© 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. 10-GEMMASCOPE-RES-131K
    7. 15576
    Prev
    Next
    INDEX
    Explanations

    code declarations and function calls

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     (
    -2.23
     each
    -1.82
     all
    -1.66
     =
    -1.55
    TO
    -1.46
     :
    -1.45
    違います
    -1.41
     не
    -1.41
     все
    -1.40
     как
    -1.40
    POSITIVE LOGITS
     %),
    1.87
    toluene
    1.85
    rosion
    1.77
     %).
    1.56
    apter
    1.55
    ethane
    1.49
    --;
    1.48
    +
    1.48
    bilt
    1.44
     jeśli
    1.44
    Activations Density 0.045%

    No Known Activations