© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85479
    Prev
    Next
    INDEX
    Explanations

    F.I.S.Co. H.I.V.E

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

    The neuron fires on numeric citation markers—numbers (often with decimals) in parentheses or standalone (e.g. volume, page, or edition numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -2.58
    .......
    -1.88
    发表于
    -1.77
     I
    -1.73
    ти
    -1.63
    There
    -1.63
    .....
    -1.62
    责编
    -1.61
    ........
    -1.61
     misguided
    -1.60
    POSITIVE LOGITS
     such
    2.11
    </h1>
    1.93
     the
    1.73
    and
    1.69
    "}}>
    1.63
    where
    1.63
     tivi
    1.60
    ak
    1.59
    {
    1.58
    erweise
    1.57
    Activations Density 0.061%

    No Known Activations