© 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. 32790
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, errors, classification

    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
    為に
    -1.01
    ごとの
    -0.96
    categorized
    -0.95
     ſeveral
    -0.93
     collectie
    -0.91
     Diese
    -0.91
    vre
    -0.89
     seule
    -0.88
     Versand
    -0.88
     möchtest
    -0.87
    POSITIVE LOGITS
     with
    1.16
    家が
    1.05
    ódz
    1.05
     requires
    1.02
    　※
    0.98
     in
    0.98
    家は
    0.97
    衛
    0.97
    ppings
    0.96
     specialmente
    0.96
    Activations Density 0.037%

    No Known Activations