© 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. 57021
    Prev
    Next
    INDEX
    Explanations

    code syntax, symbols, and punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    held
    -0.74
    ielen
    -0.70
     pyl
    -0.67
    aS
    -0.64
    lund
    -0.64
     held
    -0.64
    Spray
    -0.63
    ochet
    -0.63
    十大
    -0.62
    خر
    -0.61
    POSITIVE LOGITS
    聩
    0.77
     lezioni
    0.66
     Frankie
    0.66
    Frankie
    0.66
    厥
    0.66
    Petrol
    0.66
     resistant
    0.63
    GtkWidget
    0.62
     gebaut
    0.62
     институ
    0.62
    Activations Density 0.061%

    No Known Activations