© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38609
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron fires on numeric tokens—especially multi‐digit numerical sequences (e.g. long runs of digits in code or data).

    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
     பிர
    -0.77
    ření
    -0.75
    営業時間
    -0.73
     rebus
    -0.73
    병
    -0.71
    Bre
    -0.69
     conical
    -0.69
     Tors
    -0.68
    amycin
    -0.68
    emie
    -0.68
    POSITIVE LOGITS
     Answers
    0.91
     Pack
    0.88
     Unterschiede
    0.84
    УП
    0.82
     Atta
    0.79
    aquin
    0.79
    ixar
    0.79
     NEAR
    0.78
     المحت
    0.77
    Pack
    0.75
    Activations Density 0.173%

    No Known Activations