© 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. 10-GEMMASCOPE-RES-131K
    7. 19908
    Prev
    Next
    INDEX
    Explanations

    historical eras and named events

    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
     a
    -1.95
     speichern
    -1.66
     wohnung
    -1.54
     küche
    -1.43
     девя
    -1.37
     zdarma
    -1.36
     autre
    -1.34
     manuell
    -1.33
     детских
    -1.33
     jahr
    -1.33
    POSITIVE LOGITS
     Affaires
    1.49
     लेकिन
    1.45
    ны
    1.38
    ęcie
    1.35
     '';
    1.32
    旒
    1.31
    زند
    1.31
    FFIX
    1.30
     You
    1.28
    ęcia
    1.26
    Activations Density 0.059%

    No Known Activations