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. 8243
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Then
    -0.75
     or
    -0.75
    
    -0.74
     off
    -0.74
     from
    -0.74
    There
    -0.74
     on
    -0.73
    From
    -0.72
     alone
    -0.71
     múltiple
    -0.71
    POSITIVE LOGITS
    czeniu
    0.87
    跄
    0.86
    tière
    0.85
    εια
    0.84
     pomys
    0.84
     Bemerkungen
    0.84
     protégé
    0.82
     Arrest
    0.82
    jonijiet
    0.82
    imes
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.