© 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. 127651
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ruptedException
    -1.07
    });*/
    -1.06
    kese
    -1.06
     artesanato
    -1.06
     ukry
    -1.05
     cliquez
    -1.04
     möge
    -1.02
    celana
    -1.00
     esportes
    -1.00
     pitié
    -0.99
    POSITIVE LOGITS
     and
    1.49
    ㌧
    1.07
    了许多
    1.00
    OBJET
    0.97
    了不少
    0.95
     Fußballspieler
    0.91
     entraîner
    0.90
    CURSO
    0.90
    orial
    0.89
    plication
    0.88
    Activations Density 0.042%

    No Known Activations