© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    example sentence marker

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

    This neuron effectively never activates for any ordinary word or phrase—it stays dormant and doesn’t pick out any pattern.

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

    large blocks of whitespace or paragraph breaks between sections of text.

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

    phrases using the “at one’s doorstep” idiom to indicate something arriving or being immediately nearby.

    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
    Presentation
    0.66
    Что
    0.64
    VERY
    0.61
    0.60
    Arizona
    0.59
    概述
    0.59
    彩
    0.59
    Trong
    0.58
    ORGAN
    0.58
    Olá
    0.56
    POSITIVE LOGITS
     segera
    0.63
     cuentas
    0.61
     contará
    0.59
     subcluster
    0.58
     unabhängig
    0.58
     gewährle
    0.55
     berücksicht
    0.55
     bénéficier
    0.55
     régions
    0.55
    secutive
    0.55
    Activations Density 0.001%

    No Known Activations