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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15331
    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
    BeforeClass
    -1.03
    tungen
    -0.99
    滇
    -0.89
    跸
    -0.89
     않는
    -0.87
     %).
    -0.87
     adhe
    -0.87
    skie
    -0.86
    operatively
    -0.85
    xygen
    -0.85
    POSITIVE LOGITS
    
    1.00
    今日の
    0.98
    どんな
    0.95
     elevada
    0.91
    äus
    0.89
     mantienen
    0.88
    شهر
    0.87
     بما
    0.87
     gekomen
    0.86
    achieve
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.