© 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. 65396
    Prev
    Next
    INDEX
    Explanations

    proper names, code keywords, and foreign words

    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
    潆
    -2.61
    s
    -2.59
     miljoen
    -2.23
     greateſt
    -2.09
    愎
    -2.03
    都不会
    -1.98
    In
    -1.97
    pinephrine
    -1.95
     ―
    -1.93
     colouring
    -1.91
    POSITIVE LOGITS
     erstes
    2.83
    秾
    2.77
    _
    2.59
     pomaga
    2.41
     '
    2.38
     помогает
    2.33
     tutaj
    2.30
    н
    2.28
    ൎ
    2.27
     handful
    2.25
    Activations Density 0.001%

    No Known Activations