© 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. 69538
    Prev
    Next
    INDEX
    Explanations

    code comments and file headers

    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
     our
    -1.99
     his
    -1.92
     it
    -1.73
    ſtra
    -1.66
     организаций
    -1.59
     жаль
    -1.55
     begin
    -1.52
     {
    -1.52
     головой
    -1.50
     документов
    -1.48
    POSITIVE LOGITS
    '
    2.06
    ременно
    1.50
     لذا
    1.47
     
    1.46
     整
    1.45
    関する
    1.43
    这让
    1.42
     puramente
    1.42
     $\&$
    1.38
    寥
    1.38
    Activations Density 0.007%

    No Known Activations