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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 232
    Prev
    Next
    INDEX
    Explanations

    state court case names

    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
     Bourne
    -0.73
    box
    -0.70
    Preference
    -0.68
    meras
    -0.67
     available
    -0.67
     Igor
    -0.67
    认
    -0.67
     stimulated
    -0.67
    ociação
    -0.67
    uing
    -0.66
    POSITIVE LOGITS
    tray
    0.69
    Tray
    0.67
     MRP
    0.66
     RouterModule
    0.65
    Género
    0.63
     офи
    0.63
    ffd
    0.63
    gräns
    0.62
     Keine
    0.61
     coiff
    0.61
    Activations Density 0.064%

    No Known Activations