© 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. 7410
    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
     to
    -1.16
    O
    -1.12
    了承
    -1.11
    P
    -1.04
    ly
    -1.04
    ｢
    -1.03
    lew
    -1.03
    pensive
    -1.02
    A
    -1.02
    覚えて
    -1.02
    POSITIVE LOGITS
    Lịch
    1.37
     récla
    1.30
     évo
    1.23
    Weeks
    1.17
     étab
    1.14
    зеро
    1.13
     adatta
    1.12
     vierten
    1.10
     Nedir
    1.09
     trouxe
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.