© 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. 9817
    Prev
    Next
    INDEX
    Explanations

    images, layouts, and positions

    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
    Ứng
    -1.45
    slidesToShow
    -1.37
     detalló
    -1.33
     nguyễn
    -1.23
    ственном
    -1.20
    谙
    -1.16
     byly
    -1.16
     brauchst
    -1.15
     indicó
    -1.15
    агности
    -1.15
    POSITIVE LOGITS
     foreground
    1.27
     autobuses
    1.17
    空間
    1.11
     Moderato
    1.09
     kuda
    1.06
     valla
    1.06
    termilk
    1.05
     bosques
    1.05
     Giochi
    1.04
     images
    1.03
    Activations Density 0.048%

    No Known Activations