© 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. 7638
    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
     realizar
    -1.09
    ふり
    -0.94
    kozá
    -0.90
     fortal
    -0.88
    恶意
    -0.87
     culmin
    -0.85
     晶
    -0.85
     correa
    -0.85
     coordinate
    -0.84
     definir
    -0.84
    POSITIVE LOGITS
     Vergnügen
    1.09
    ők
    1.01
    aratus
    0.98
     inimes
    0.96
     īpa
    0.95
     piemē
    0.94
     Gruß
    0.93
    nikova
    0.93
    GGGG
    0.93
     творчество
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.