© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15450
    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
     or
    -1.05
     ktorí
    -0.97
     siyang
    -0.93
     ""));
    -0.92
    *{\
    -0.90
    或者是
    -0.89
     };
    -0.89
    icylic
    -0.88
     применение
    -0.87
    裏面
    -0.86
    POSITIVE LOGITS
     排骨
    1.11
    姽
    1.06
     starten
    1.05
     jednak
    1.03
    骇
    1.02
     شروع
    1.02
    毟
    0.97
    Council
    0.95
    ikkert
    0.95
     ادامه
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.