© 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. 106448
    Prev
    Next
    INDEX
    Explanations

    computing center or finite sets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     rape
    -1.05
     reddish
    -0.99
     re
    -0.93
     rheumatoid
    -0.90
     rumah
    -0.89
     Probably
    -0.89
    ),
    -0.87
     reduce
    -0.86
     receptive
    -0.85
     rupture
    -0.85
    POSITIVE LOGITS
    bezpiecz
    1.03
     カジュアル
    1.03
    蜜
    0.97
     suspic
    0.94
     pastillas
    0.94
     hygge
    0.91
     новое
    0.89
    weisungen
    0.88
     SEX
    0.87
     totiž
    0.86
    Activations Density 0.411%

    No Known Activations