© 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. 10-GEMMASCOPE-RES-131K
    7. 119414
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding

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

    colons in code, especially after encoding declarations, comments, and control flow statements in programming languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects colon punctuation tokens (":"), as used in coding declarations and comment directives.

    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
    [
    -2.56
    '
    -2.25
    -
    -2.19
    ↵↵↵
    -2.06
     
    -2.02
     "
    -2.00
    {
    -1.98
    o
    -1.91
    "
    -1.91
    <b>
    -1.90
    POSITIVE LOGITS
    ússia
    2.05
    🫅
    1.93
    vikle
    1.88
    国家的
    1.77
    wezig
    1.77
    kadang
    1.76
     kvadrat
    1.75
    妡
    1.75
    rozum
    1.73
     fotografii
    1.73
    Activations Density 0.010%

    No Known Activations