© 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. 15676
    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
     what
    -1.62
     our
    -1.52
     holdt
    -1.46
    葑
    -1.46
     It
    -1.43
     three
    -1.37
     several
    -1.35
     five
    -1.34
    饪
    -1.32
     okno
    -1.31
    POSITIVE LOGITS
    絰
    1.45
    the
    1.25
     セットアップ
    1.23
     tante
    1.20
     dessa
    1.17
     facili
    1.15
     BIBLIO
    1.12
     depic
    1.12
    銠
    1.12
    ════
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.