© 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. 22791
    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
     perquè
    -1.44
     لأنه
    -1.34
     своих
    -1.31
     свої
    -1.29
     ใช้
    -1.27
    新鲜
    -1.23
     treball
    -1.23
    Только
    -1.22
     porque
    -1.20
     svou
    -1.20
    POSITIVE LOGITS
     is
    1.84
     including
    1.66
     that
    1.59
     occhi
    1.57
     such
    1.53
     упаковка
    1.50
    JHEP
    1.50
     the
    1.43
     to
    1.40
    佰
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.