© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2430
    Prev
    Next
    INDEX
    Explanations

    endanger children or individuals

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on strong, mission‐oriented action verbs (e.g., “promoting,” “protect,” “advance,” “encourage”) typically found in organizational or policy statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words related to organizational missions and goals, particularly verbs describing actions to support, improve, or advance initiatives.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    proactive, purpose-driven action verbs that express protecting, advancing, or improving something, often in mission or policy-style statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jeopardize
    0.54
     lắm
    0.52
     pollute
    0.52
     reassure
    0.47
     forgo
    0.46
     guarantee
    0.46
     garanti
    0.44
    ದಲ
    0.44
    賺
    0.44
     HYDRO
    0.43
    POSITIVE LOGITS
    previous
    0.46
    といった
    0.43
     গিয়ে
    0.43
     среды
    0.43
     czyli
    0.43
     ehemaligen
    0.43
     verschiedene
    0.42
     sowie
    0.42
    are
    0.42
     wygl
    0.42
    Activations Density 0.031%

    No Known Activations