© 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. 71406
    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
     treff
    -1.29
     bahwa
    -1.26
    exemple
    -1.22
    pasang
    -1.20
     Почему
    -1.20
     elucid
    -1.19
     самой
    -1.19
    ’
    -1.18
    了你
    -1.18
    髎
    -1.17
    POSITIVE LOGITS
     it
    1.74
    啻
    1.28
    ﻊ
    1.23
    🢒
    1.19
     any
    1.16
    補助
    1.16
    arded
    1.13
    gating
    1.11
    禤
    1.11
     anyone
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.