© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11883
    Prev
    Next
    INDEX
    Explanations

    programming definitions and calls

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

    function calls or keywords that define or declare functions and modules in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     
    -1.73
    はもう
    -1.38
    垕
    -1.36
     their
    -1.35
     misschien
    -1.33
     simply
    -1.29
    <bos>
    -1.27
     to
    -1.26
    pernicus
    -1.26
    殃
    -1.24
    POSITIVE LOGITS
    妩
    1.74
    %");
    1.67
    >`;
    1.65
    顚
    1.59
    ')";
    1.59
     общения
    1.56
    ()");
    1.56
     rapidement
    1.53
     якості
    1.51
    ://
    1.50
    Activations Density 0.028%

    No Known Activations