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. 8541
    Prev
    Next
    INDEX
    Explanations

    Base-T, Breeders, Teach

    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
    もあります
    -0.73
     gelombang
    -0.69
     unidad
    -0.68
    ICI
    -0.68
    BUFF
    -0.67
    MATIC
    -0.67
    ريح
    -0.67
    Otto
    -0.66
    DIR
    -0.64
     零
    -0.64
    POSITIVE LOGITS
     rejection
    0.73
     Hors
    0.71
     barista
    0.68
    Hors
    0.64
     therefrom
    0.64
     Oceania
    0.63
     през
    0.63
    갓
    0.62
     Rejection
    0.62
    Assault
    0.62
    Activations Density 0.083%

    No Known Activations