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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110436
    Prev
    Next
    INDEX
    Explanations

    Q: questions or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Franchise
    -0.83
     sublimation
    -0.73
     취
    -0.71
     Pulse
    -0.70
    Татьяна
    -0.69
    グロー
    -0.69
     Seva
    -0.68
    ̲
    -0.68
     spher
    -0.68
     fidu
    -0.67
    POSITIVE LOGITS
    []}
    0.83
    []){
    0.80
    ساس
    0.74
    ಃ
    0.73
     ratio
    0.73
    疵
    0.73
    ネート
    0.73
    wes
    0.73
     マスク
    0.73
    ratios
    0.72
    Activations Density 0.004%

    No Known Activations