© 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. 92177
    Prev
    Next
    INDEX
    Explanations

    Recorder prepare, certificates provided, built up, link new

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

    The neuron primarily activates on numeric literals (sequences of digits) appearing in code, comments, or text.

    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
    十
    -0.92
    金
    -0.84
    AS
    -0.84
    as
    -0.79
    向
    -0.79
     dix
    -0.77
     金
    -0.77
    AndWait
    -0.76
    angu
    -0.75
    COIN
    -0.75
    POSITIVE LOGITS
    onClose
    0.74
     exalted
    0.73
     мѣ
    0.72
    ねー
    0.68
     Kot
    0.67
     cutlery
    0.67
     electors
    0.66
     despotism
    0.65
    Elephant
    0.65
    vident
    0.64
    Activations Density 0.546%

    No Known Activations