© 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. 102429
    Prev
    Next
    INDEX
    Explanations

    select

    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
    ,”
    -1.97
     are
    -1.63
    ahuila
    -1.57
    ”（
    -1.57
     impe
    -1.55
    咥
    -1.52
    you
    -1.52
    able
    -1.51
    up
    -1.48
     palio
    -1.48
    POSITIVE LOGITS
     a
    2.00
     changé
    1.91
     aplicaciones
    1.84
     '
    1.80
     correto
    1.73
    КОВ
    1.72
    时间
    1.70
     peligros
    1.70
     pensent
    1.63
    "
    1.61
    Activations Density 0.019%

    No Known Activations