© 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. 22-GEMMASCOPE-RES-131K
    7. 25065
    Prev
    Next
    INDEX
    Explanations

    golang, aws, errors, openapi, generator

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     such
    -1.14
    ⿱
    -1.10
    pullover
    -1.03
     details
    -1.01
    Télécharger
    -0.99
    bkg
    -0.98
    DEO
    -0.97
    lln
    -0.96
    secara
    -0.96
    Facile
    -0.94
    POSITIVE LOGITS
    \
    1.26
     или
    1.20
     получилось
    1.12
     DataGridView
    1.11
     >=",
    1.07
     UITableViewCell
    1.07
    新加坡
    1.04
     ними
    1.03
     еще
    1.02
    nienie
    1.02
    Activations Density 0.030%

    No Known Activations