© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13529
    Prev
    Next
    INDEX
    Explanations

    benefits and advantages

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

    The neuron activates strongly on occurrences of “benefit” (and its plural “benefits”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     traumas
    0.73
     Zanu
    0.72
     sucesso
    0.69
    ῥ
    0.68
     success
    0.66
    니다
    0.66
    Rationale
    0.66
     succeed
    0.66
     affect
    0.65
     успеш
    0.65
    POSITIVE LOGITS
     उठाकर
    0.66
     올라
    0.66
    માં
    0.66
    ရှိ
    0.66
     hindsight
    0.66
    🎊
    0.66
    🌈
    0.65
    alysis
    0.63
    🍱
    0.63
     Package
    0.63
    Activations Density 0.206%

    No Known Activations