© 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. 106132
    Prev
    Next
    INDEX
    Explanations

    colors and themes

    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
    Раз
    -0.75
    一把
    -0.71
    .*;
    -0.70
    原创
    -0.70
     дать
    -0.69
    --;
    -0.69
    ../
    -0.69
    Nós
    -0.69
    ::{
    -0.68
    镍
    -0.68
    POSITIVE LOGITS
     Colors
    1.88
    Colors
    1.48
     Color
    1.07
     colors
    0.97
     Theme
    0.92
     accent
    0.85
    的颜色
    0.83
     accents
    0.83
    ƨ
    0.82
    Theme
    0.80
    Activations Density 0.001%

    No Known Activations