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. 7953
    Prev
    Next
    INDEX
    Explanations

    names containing God

    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
     něko
    -0.76
    来讲
    -0.75
    ed
    -0.73
    wj
    -0.72
    unpublished
    -0.71
    around
    -0.71
     assail
    -0.69
    UCIÓN
    -0.69
    鹸
    -0.68
     alrededor
    -0.67
    POSITIVE LOGITS
     forbid
    1.20
    awful
    1.00
     knows
    0.99
     fearing
    0.92
     help
    0.91
     willing
    0.86
    knows
    0.85
     Uso
    0.82
    paren
    0.82
    專輯
    0.81
    Activations Density 0.010%

    No Known Activations