© 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. 22-GEMMASCOPE-RES-131K
    7. 25014
    Prev
    Next
    INDEX
    Explanations

    git branches and checkout

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ׇ
    -1.14
     Teknik
    -1.04
     вже
    -0.98
     harap
    -0.96
     dilap
    -0.94
     kolom
    -0.93
     seru
    -0.93
    меч
    -0.92
     marah
    -0.90
     rapi
    -0.89
    POSITIVE LOGITS
    你和
    1.14
     initComponents
    1.00
     schwarzen
    0.98
    oniec
    0.93
    NamedQueries
    0.93
    erialize
    0.90
     głę
    0.90
     sự
    0.89
     addition
    0.88
     discapacidad
    0.88
    Activations Density 0.001%

    No Known Activations