© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63603
    Prev
    Next
    INDEX
    Explanations

    dates: month/day

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

    The neuron fires on numeric identifiers and version‐style tokens (e.g. dates, revision numbers, code/ID 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
     leggere
    -0.77
    plaat
    -0.73
    жие
    -0.72
     jongen
    -0.70
     esfuerzos
    -0.69
    ChangePassword
    -0.68
    pedro
    -0.66
    frau
    -0.66
    砵
    -0.65
    plato
    -0.64
    POSITIVE LOGITS
     Main
    0.75
    ピン
    0.72
    フォー
    0.69
     payoff
    0.68
    yonel
    0.68
    пти
    0.68
     संस्
    0.68
    CN
    0.68
    REP
    0.66
    Main
    0.65
    Activations Density 0.095%

    No Known Activations