© 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. 40095
    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
     after
    -1.28
     at
    -1.22
    ↵↵
    -1.18
     as
    -1.14
     three
    -1.07
     six
    -1.06
     before
    -1.03
     five
    -1.02
     in
    -1.02
     to
    -0.96
    POSITIVE LOGITS
     élas
    1.12
    bda
    1.02
     sourdough
    0.98
     fréquent
    0.98
    buie
    0.96
     verge
    0.96
     Halal
    0.95
     laterale
    0.94
    🍙
    0.94
    ⎚
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.