© 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. 22625
    Prev
    Next
    INDEX
    Explanations

    Soviet Union history

    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
     of
    -2.48
    刧
    -2.05
     the
    -1.80
    This
    -1.78
     at
    -1.66
     镇
    -1.66
     女人
    -1.63
    缐
    -1.63
     αυτή
    -1.63
    ၞ
    -1.63
    POSITIVE LOGITS
    ↵↵
    2.16
     
    1.97
     seleccionadas
    1.80
     eléctricas
    1.76
     favoritas
    1.70
    ⸨
    1.65
     privadas
    1.65
     The
    1.62
     föränd
    1.57
    ↵↵↵
    1.53
    Activations Density 0.027%

    No Known Activations