© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    zh strings in file paths and identifiers

    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
    ⎔
    -3.16
    嚒
    -2.67
    崀
    -2.66
    峮
    -2.66
    躄
    -2.59
    鉏
    -2.56
     segn
    -2.56
    茕
    -2.52
    
    -2.52
    蹀
    -2.48
    POSITIVE LOGITS
    '
    2.39
    *
    2.19
    (
    2.17
    刧
    2.16
    餵
    2.13
    ate
    2.08
     Züge
    2.02
    cherichia
    2.02
    馮
    2.02
    On
    2.00
    Activations Density 0.001%

    No Known Activations