© 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. 40117
    Prev
    Next
    INDEX
    Explanations

    programming code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    us
    -2.23
    -2.16
    ens
    -1.95
    out
    -1.73
    te
    -1.68
    Y
    -1.65
    me
    -1.63
    in
    -1.62
    en
    -1.59
    id
    -1.57
    POSITIVE LOGITS
    豋
    1.86
     JUDICIAL
    1.75
     MINNESOTA
    1.70
    vejec
    1.68
     PHILOS
    1.65
    heureusement
    1.63
     WORKSHOP
    1.63
    ﻐ
    1.63
     RAILWAY
    1.63
     WILDLIFE
    1.61
    Activations Density 0.009%
    No Known Activations