© 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. 68984
    Prev
    Next
    INDEX
    Explanations

    Irving, Morton, Roth

    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
    \
    -3.16
    er
    -3.16
    end
    -3.06
    在我
    -3.05
    on
    -2.63
    
    -2.55
     endeavors
    -2.52
    急に
    -2.48
    曾经
    -2.45
    begin
    -2.42
    POSITIVE LOGITS
    酲
    3.23
    饹
    2.81
    灕
    2.53
    옻
    2.52
     of
    2.50
    鄠
    2.47
    遹
    2.47
    ↑↑↑</
    2.44
    ÇÃO
    2.44
     Bedür
    2.39
    Activations Density 0.003%

    No Known Activations