© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20263
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ()};
    -1.09
    óta
    -1.01
     спасибо
    -1.00
    quête
    -0.99
     шт
    -0.96
    "};
    -0.96
     }}>
    -0.95
    
    -0.95
     Pologne
    -0.95
    踭
    -0.94
    POSITIVE LOGITS
     without
    0.96
    ancang
    0.95
    だそうです
    0.90
    5
    0.90
     Krieges
    0.90
    โน
    0.85
     defining
    0.83
     unrelenting
    0.82
     competent
    0.82
    なみ
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.