© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95497
    Prev
    Next
    INDEX
    Explanations

    United States France Germany Egypt

    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
    をする
    -1.05
     it
    -0.96
     lez
    -0.96
    ,
    -0.96
     up
    -0.96
    姥
    -0.95
    insee
    -0.94
     in
    -0.93
    kath
    -0.93
    kimono
    -0.92
    POSITIVE LOGITS
     høre
    1.27
     kontakta
    1.18
     vilja
    1.09
     kvinnor
    1.05
    пература
    1.04
    いきなり
    1.02
     møte
    1.00
     mineures
    0.99
    However
    0.98
     カ
    0.98
    Activations Density 0.057%

    No Known Activations