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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11874
    Prev
    Next
    INDEX
    Explanations

    not included or associated

    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_22/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
     кілька
    -1.04
     siè
    -0.99
     plusieurs
    -0.98
    enforce
    -0.94
    entown
    -0.93
     Daftar
    -0.91
    endfor
    -0.90
    ecake
    -0.89
    轻声
    -0.87
     ascertained
    -0.87
    POSITIVE LOGITS
     included
    1.20
     contributing
    1.10
     contribute
    1.03
    参与
    0.99
    太大
    0.94
    參與
    0.93
     part
    0.93
     contributed
    0.90
     considérons
    0.90
     are
    0.88
    Activations Density 0.058%

    No Known Activations