© 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. 10-GEMMASCOPE-RES-131K
    7. 85628
    Prev
    Next
    INDEX
    Explanations

    a comma followed by a word

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

    The neuron fires on numeric tokens (multi‐digit numbers and related numeric punctuation).

    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
    푉
    -2.03
    ansvar
    -1.73
    푢
    -1.69
    퐿
    -1.67
     алюми
    -1.65
    trz
    -1.63
    ;%%
    -1.63
    Preparazione
    -1.61
    transpiration
    -1.58
    ざ
    -1.58
    POSITIVE LOGITS
     it
    2.61
     they
    2.36
     but
    2.23
    '
    2.03
    ’
    1.83
    4
    1.81
    =
    1.79
     when
    1.78
     here
    1.72
    殽
    1.64
    Activations Density 0.220%

    No Known Activations