© 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. 47250
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE TABLE statements

    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
     type
    -1.16
     tipo
    -1.05
    type
    -1.04
     TYPE
    -1.00
    TYPE
    -0.95
    عار
    -0.92
     types
    -0.91
    Tipo
    -0.90
     tipe
    -0.88
     kiểu
    -0.88
    POSITIVE LOGITS
     erzeugen
    0.81
    rida
    0.79
    eratops
    0.78
    が付いて
    0.77
     أكتوبر
    0.77
    CAPÍTULO
    0.76
     impeller
    0.76
    Och
    0.76
     μας
    0.75
    ":[
    0.75
    Activations Density 0.030%

    No Known Activations