© 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. 34-GEMMASCOPE-RES-131K
    7. 79329
    Prev
    Next
    INDEX
    Explanations

    GNU software and licenses

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     quench
    -0.90
     投稿
    -0.80
     леса
    -0.77
    AHH
    -0.75
    LISTEN
    -0.75
    companied
    -0.75
    Meso
    -0.75
     commentaries
    -0.75
    salomon
    -0.75
     Adopted
    -0.74
    POSITIVE LOGITS
     GoogleFonts
    0.80
     NUM
    0.78
     pres
    0.77
    viations
    0.73
     ничего
    0.71
     пользователей
    0.70
    ouser
    0.69
    scanf
    0.69
     DBNull
    0.69
    baum
    0.69
    Activations Density 0.031%

    No Known Activations