Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8597
    Prev
    Next
    INDEX
    Explanations

    logging levels and configuration

    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
    LMAO
    -0.81
     学习
    -0.73
     آم
    -0.73
     ام
    -0.72
    бирать
    -0.69
    זרה
    -0.69
     Holistic
    -0.68
    )}]{
    -0.68
    Cliquez
    -0.67
     susp
    -0.66
    POSITIVE LOGITS
    SEVERE
    1.00
     fines
    0.95
    fine
    0.93
     fine
    0.85
    FIN
    0.84
    giatan
    0.84
    handlers
    0.81
    感器
    0.81
    FINE
    0.81
    CONFIG
    0.80
    Activations Density 0.022%

    No Known Activations