© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    company name and legal case identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     pavillon
    -1.13
    +'</
    -1.07
    ensed
    -1.07
    copically
    -1.04
     autorisation
    -1.04
     😌
    -1.04
     renon
    -1.03
    entado
    -1.03
     fiche
    -1.02
     Formen
    -1.02
    POSITIVE LOGITS
     my
    1.30
     its
    1.22
     “
    1.20
     allegedly
    1.17
     после
    1.17
     "
    1.13
     behalten
    1.13
     of
    1.12
     how
    1.12
     not
    1.11
    Activations Density 0.453%

    No Known Activations