© 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. 64429
    Prev
    Next
    INDEX
    Explanations

    spatio-temporally inappropriate

    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
     REPRESENTATIVES
    -1.06
     meras
    -1.03
    fährt
    -1.02
    ：　
    -1.02
     igre
    -0.98
    єте
    -0.97
     geng
    -0.97
    hmä
    -0.95
    vänd
    -0.94
    noteq
    -0.93
    POSITIVE LOGITS
     other
    1.11
    It
    1.05
     that
    1.03
     thereafter
    0.97
     confiable
    0.96
     [
    0.93
    美しく
    0.91
     then
    0.91
     dök
    0.91
    []
    0.91
    Activations Density 0.159%

    No Known Activations