© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98742
    Prev
    Next
    INDEX
    Explanations

    games, retro, and specific names

    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
    Negative Logits
     steam
    -1.30
    SanPham
    -1.23
     summer
    -1.20
     siting
    -1.19
     کرنے
    -1.16
     meteen
    -1.16
     السياس
    -1.16
    𐐪
    -1.15
    ResetPassword
    -1.14
     taint
    -1.13
    POSITIVE LOGITS
    dienne
    1.55
    romeda
    1.55
    alties
    1.54
    isier
    1.45
     endast
    1.42
    cketed
    1.41
     magari
    1.40
    vertible
    1.40
    titial
    1.38
     preſ
    1.36
    Activations Density 0.005%

    No Known Activations