© 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. 24960
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     both
    -1.15
     zarówno
    -1.05
    unakan
    -1.02
     eight
    -0.99
     about
    -0.97
    giacca
    -0.96
     including
    -0.96
     November
    -0.95
     only
    -0.94
    勵
    -0.94
    POSITIVE LOGITS
    ('/:
    1.17
     DOD
    1.13
     capaces
    1.10
     novamente
    1.10
     crean
    1.09
     plongée
    1.07
     yeniden
    1.06
     Aucune
    1.05
     herencia
    1.04
     toutefois
    1.03
    Activations Density 0.001%

    No Known Activations