© 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. 6765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     if
    -1.12
     people
    -1.09
    Если
    -1.00
     plethora
    -0.93
    People
    -0.93
     Pony
    -0.89
     Di
    -0.88
    \
    -0.88
    Тогда
    -0.85
    حث
    -0.84
    POSITIVE LOGITS
     Resultados
    1.09
    面白い
    1.07
     estrat
    1.04
    ി
    1.03
    .}(
    1.03
    <$
    1.03
     flera
    1.02
    亹
    1.02
     ouvir
    1.02
     zanahoria
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.