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. 8633
    Prev
    Next
    INDEX
    Explanations

    failed connection or cache

    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
    ไตล์
    -0.65
    роид
    -0.65
     Hạ
    -0.64
     IPv
    -0.64
     producir
    -0.63
     evils
    -0.62
    เหตุ
    -0.61
    STYLE
    -0.61
    producing
    -0.60
     Producción
    -0.60
    POSITIVE LOGITS
    țion
    0.75
    tsky
    0.73
    APTER
    0.71
    Fah
    0.71
     diter
    0.71
    redu
    0.70
    اا
    0.69
     rewriting
    0.69
    Öl
    0.69
     تجاری
    0.69
    Activations Density 0.038%

    No Known Activations