© 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. 106299
    Prev
    Next
    INDEX
    Explanations

    Photography website

    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
     More
    -0.74
    carpus
    -0.72
     school
    -0.72
     where
    -0.71
     would
    -0.69
    More
    -0.69
     usually
    -0.68
     Й
    -0.67
     maybe
    -0.67
    Pranala
    -0.66
    POSITIVE LOGITS
     pres
    1.00
     Truss
    0.95
     STAGE
    0.93
     Phases
    0.88
     unités
    0.85
     Potassium
    0.85
     Toon
    0.85
     ativos
    0.84
    ریف
    0.84
    ₁(
    0.84
    Activations Density 0.001%

    No Known Activations