© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77202
    Prev
    Next
    INDEX
    Explanations

    legislation, bills, and official measures

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

    The neuron fires on tokens containing digits—e.g. numerical identifiers, years, measure or proposition numbers, citation and version 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_34/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
    ට
    -0.69
    表達
    -0.67
    mContext
    -0.66
     miliar
    -0.66
     Experience
    -0.66
    Former
    -0.65
    nivå
    -0.65
    prechung
    -0.64
     Former
    -0.63
    logLevel
    -0.63
    POSITIVE LOGITS
    pou
    0.77
     Passes
    0.71
    edge
    0.69
    <0xA3>
    0.68
    ꈍ
    0.68
    iação
    0.67
     partis
    0.65
    ticket
    0.65
    ctest
    0.65
    合作
    0.64
    Activations Density 0.050%

    No Known Activations