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. 8221
    Prev
    Next
    INDEX
    Explanations

    license and distribution notices

    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
     EVERYTHING
    -0.87
     tudo
    -0.85
     Kullan
    -0.85
    ādā
    -0.82
     offseason
    -0.80
    Sci
    -0.79
     Američ
    -0.77
    '),
    
    -0.77
    
    -0.77
     everything
    -0.76
    POSITIVE LOGITS
    heute
    0.79
     again
    0.78
     days
    0.75
    ibles
    0.75
     enough
    0.73
     argento
    0.72
    ┓
    0.71
    しょう
    0.70
    nullptr
    0.70
    idet
    0.70
    Activations Density 0.403%

    No Known Activations