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. 137
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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
     better
    -0.84
     more
    -0.84
     some
    -0.82
     fortsetter
    -0.81
     reportedly
    -0.80
    some
    -0.79
     alcuni
    -0.79
    olverine
    -0.78
    
    -0.78
     above
    -0.77
    POSITIVE LOGITS
     Gln
    1.01
     ,\
    0.99
     ,
    
    0.94
    ткий
    0.93
    ྲ
    0.92
     )
    
    0.91
     Faça
    0.91
     ,
    0.90
     Daarnaast
    0.88
    >;
    0.88
    Activations Density 0.038%

    No Known Activations