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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19942
    Prev
    Next
    INDEX
    Explanations

    showing his face or body

    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
    Not in Any Lists

    No Comments

    Negative Logits
    この
    -1.41
     this
    -1.39
    ओं
    -1.30
    -1.28
    й
    -1.27
    ガンダム
    -1.27
    CCER
    -1.25
     jambe
    -1.24
    ).”
    -1.23
     TICKETS
    -1.23
    POSITIVE LOGITS
     двумя
    1.58
    ppsala
    1.55
     состава
    1.54
     thier
    1.51
     ….
    1.46
     mehrere
    1.46
     Showing
    1.46
     unſ
    1.46
     senza
    1.46
     realizar
    1.46
    Activations Density 0.038%
    No Known Activations