© 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. 74881
    Prev
    Next
    INDEX
    Explanations

    programming keywords definitions

    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
     nadru
    -1.73
    Vlast
    -1.56
    interpr
    -1.54
     perdre
    -1.54
     llavero
    -1.52
     siè
    -1.51
     cinto
    -1.50
     великолеп
    -1.48
    
    -1.47
     restant
    -1.46
    POSITIVE LOGITS
     in
    1.99
     as
    1.98
     for
    1.87
     (
    1.77
    (
    1.71
    !
    1.68
    —
    1.65
    o
    1.62
    en
    1.61
    ?
    1.55
    Activations Density 0.084%

    No Known Activations