© 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. 103900
    Prev
    Next
    INDEX
    Explanations

    programming code elements

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

    underscores in function or method names, particularly in programming 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
    <h2>
    -1.95
    0
    -1.66
    seven
    -1.57
     zwanzig
    -1.55
    //
    -1.49
    ;
    -1.48
    nearly
    -1.44
     charlotte
    -1.44
     tetapi
    -1.41
     ‘’
    -1.41
    POSITIVE LOGITS
     tragé
    1.66
    Гц
    1.64
     and
    1.62
     akad
    1.57
     शुर
    1.56
     moletom
    1.54
    瑧
    1.53
     rodillas
    1.49
     taky
    1.48
     rique
    1.46
    Activations Density 0.011%

    No Known Activations