© 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. 72069
    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
     enorme
    -1.43
    probably
    -1.38
     небольшой
    -1.35
    1
    -1.28
     неболь
    -1.27
     “
    -1.26
     niewiel
    -1.20
     a
    -1.20
    すごく
    -1.19
    ll
    -1.17
    POSITIVE LOGITS
    ensões
    1.35
     komentar
    1.30
    harapkan
    1.27
     próxim
    1.23
    őben
    1.23
    secution
    1.22
     retrovisor
    1.20
    zboi
    1.18
    ’，
    1.17
    ///
    1.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.