© 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. 123744
    Prev
    Next
    INDEX
    Explanations

    listing components

    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
     
    -2.03
     this
    -1.98
     as
    -1.97
     with
    -1.94
     of
    -1.80
     one
    -1.80
     we
    -1.77
     Since
    -1.75
    '
    -1.73
     wohin
    -1.72
    POSITIVE LOGITS
    苙
    2.44
    
    2.33
    朥
    2.06
    扨
    2.03
    مواد
    2.02
    厹
    2.02
     dekoratif
    1.97
     katk
    1.95
     collè
    1.92
    
    1.91
    Activations Density 0.116%

    No Known Activations