© 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. 22-GEMMASCOPE-RES-131K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    .com URLs

    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_22/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
     zusätzlichen
    -0.83
    
    -0.82
    貼り
    -0.79
    的是
    -0.78
     collaborateurs
    -0.78
     Anbau
    -0.77
    インタ
    -0.77
     öffnen
    -0.76
    〈
    -0.76
    -0.76
    POSITIVE LOGITS
    來
    1.01
    тинг
    0.93
    migrationBuilder
    0.91
    alamu
    0.90
    ترنت
    0.89
     使っ
    0.89
    尔夫
    0.88
    ptăm
    0.87
    TAX
    0.85
     kuin
    0.84
    Activations Density 0.034%

    No Known Activations