© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    gas usage and price

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

    The neuron fires on numeric tokens, spotting numbers (including multi-digit and decimal figures).

    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
    おく
    0.57
     Cards
    0.55
     Modules
    0.54
    </strong>
    0.54
     Objects
    0.54
     Variants
    0.54
     Plummer
    0.54
     Problems
    0.53
     AB
    0.52
    <
    0.52
    POSITIVE LOGITS
    ėtų
    0.62
     Москве
    0.55
    št
    0.53
    kommer
    0.53
    െന്നു
    0.52
    서비스
    0.52
    プリント
    0.50
    उन्
    0.50
     மில்லியன்
    0.50
    店頭
    0.49
    Activations Density 0.003%

    No Known Activations