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. 8561
    Prev
    Next
    INDEX
    Explanations

    checklists or specific entries

    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
     Katrina
    -0.77
     anarchy
    -0.76
     Modular
    -0.76
     commercial
    -0.74
     VIN
    -0.73
     Abt
    -0.71
    兆
    -0.71
     stall
    -0.71
    ണ
    -0.70
    commercial
    -0.70
    POSITIVE LOGITS
     Veld
    0.77
    wants
    0.76
    assassin
    0.76
    swatch
    0.75
    jamie
    0.74
     Wants
    0.72
    getUserInfo
    0.71
     Invasion
    0.71
    hockey
    0.70
     cantantes
    0.69
    Activations Density 0.021%

    No Known Activations