© 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. 99243
    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
    BufferedReader
    -1.02
    !-
    -0.96
    !
    -0.92
    /*"
    -0.91
    padek
    -0.91
     jargon
    -0.90
     kuu
    -0.90
    "-
    -0.89
    !"
    -0.88
    ஸ
    -0.88
    POSITIVE LOGITS
     agreement
    1.12
     opzioni
    1.05
    门外
    1.05
     to
    1.02
     they
    1.00
     agree
    0.96
    灑
    0.96
    
    0.94
     crítica
    0.93
    lization
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.