© 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. 64638
    Prev
    Next
    INDEX
    Explanations

    Online Store

    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
    Not in Any Lists

    No Comments

    Negative Logits
    人的
    -1.05
    нология
    -0.94
     бути
    -0.94
    )
    -0.93
    xbe
    -0.93
    velmente
    -0.92
    mmä
    -0.90
     Auflage
    -0.90
     przeznac
    -0.90
     from
    -0.89
    POSITIVE LOGITS
    César
    1.15
    Bisa
    1.08
    Klu
    1.06
    Новые
    1.06
    cestry
    1.05
     autorisation
    1.05
    åter
    1.05
    Papier
    1.05
    之为
    1.05
     }}</
    1.04
    Activations Density 0.001%

    No Known Activations