© 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. 38412
    Prev
    Next
    INDEX
    Explanations

    fan or fan-adjacent words

    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
     frantically
    -2.91
     pensaba
    -2.61
     ส์
    -2.52
    烔
    -2.50
    摃
    -2.48
     creía
    -2.45
     Vielzahl
    -2.34
    糅
    -2.34
    ⾳
    -2.33
     perfettamente
    -2.31
    POSITIVE LOGITS
    '
    2.81
    a
    2.73
     μια
    2.44
    {
    2.38
     excell
    2.27
     είναι
    2.25
    /
    2.17
    どういう
    2.16
    过来
    2.13
    He
    2.09
    Activations Density 0.005%

    No Known Activations