© 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. 6888
    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
    Sometimes
    -1.28
     mattino
    -1.20
    Fär
    -1.14
     sonno
    -1.04
     melakukannya
    -1.04
    Perhaps
    -1.04
     velg
    -1.02
    робі
    -1.01
    Typically
    -1.01
    Often
    -1.01
    POSITIVE LOGITS
    のア
    0.94
     preprint
    0.94
    avras
    0.91
     fateful
    0.91
     I
    0.90
    ata
    0.89
     к
    0.88
     nome
    0.88
    ządu
    0.88
     pursu
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.