© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12207
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation and symbols

    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
     If
    -3.03
     undeniably
    -2.69
     as
    -2.67
     Give
    -2.66
     Although
    -2.64
     Since
    -2.59
     evidently
    -2.58
     first
    -2.56
     Because
    -2.55
     drastically
    -2.53
    POSITIVE LOGITS
     Dinas
    3.16
    蓠
    2.97
    奁
    2.95
    튿
    2.84
    
    2.83
    躄
    2.72
    having
    2.64
     ridiculously
    2.63
    婠
    2.61
    냑
    2.61
    Activations Density 0.009%

    No Known Activations