© 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. 86884
    Prev
    Next
    INDEX
    Explanations

    court

    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
     kertoo
    -1.90
    导致
    -1.70
     sanoo
    -1.68
     bluse
    -1.64
     torba
    -1.60
     geda
    -1.56
    ONYMOUS
    -1.52
     hemd
    -1.52
    лик
    -1.52
     flotte
    -1.50
    POSITIVE LOGITS
    ↵↵
    1.88
     
    1.69
     at
    1.66
     to
    1.66
     as
    1.61
     not
    1.59
    N
    1.52
     bestimmten
    1.49
     up
    1.48
     frühen
    1.48
    Activations Density 0.022%

    No Known Activations