© 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. 13863
    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
     you
    -2.78
     Hinsicht
    -2.56
     после
    -2.52
     ก็
    -2.45
    งิน
    -2.42
     сентября
    -2.41
     边框
    -2.39
    ၉
    -2.31
     sebelum
    -2.28
     دولار
    -2.27
    POSITIVE LOGITS
    9
    3.81
    ties
    3.28
    m
    3.03
    裡的
    2.91
    B
    2.89
    ers
    2.80
    X
    2.75
    蕺
    2.73
    T
    2.72
    P
    2.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.