© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    titles, questions, and lists

    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
     angiel
    -1.09
    बह
    -1.03
    当然是
    -0.99
    venty
    -0.95
    不通
    -0.94
    .+\
    -0.92
    tieron
    -0.92
     kanal
    -0.91
     asti
    -0.91
    ونی
    -0.90
    POSITIVE LOGITS
     during
    0.93
     eventually
    0.92
     followed
    0.90
    Demografie
    0.88
     noiva
    0.83
     приходится
    0.83
     subsequently
    0.83
     only
    0.83
     monograph
    0.82
    Spécification
    0.82
    Activations Density 0.000%

    No Known Activations