© 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. 67517
    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
     Although
    -1.27
     these
    -1.16
     Contrary
    -1.14
     There
    -1.11
     Generally
    -1.09
     facilitating
    -1.09
    خاب
    -1.05
     although
    -1.05
     Every
    -1.04
    ८
    -1.02
    POSITIVE LOGITS
    entitled
    1.13
     actualiza
    1.11
    Duties
    1.05
    就把
    1.03
    Refunds
    1.01
    preferably
    0.97
    ,;
    0.96
    updating
    0.95
     rè
    0.94
     ò
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.