© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114217
    Prev
    Next
    INDEX
    Explanations

    clientele or IBOutlet

    np_acts-logits-general · gemini-2.5-flash-lite

    the "@" symbol, particularly in code syntax and social media handles.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
     luto
    -2.42
    瑧
    -2.38
    There
    -2.33
    Just
    -2.27
     encourage
    -2.25
     emporio
    -2.22
    ↵
    -2.22
    You
    -2.11
     tigre
    -2.09
    just
    -2.05
    POSITIVE LOGITS
     WHILE
    2.83
    氿
    2.78
     😁
    2.73
    enablog
    2.66
     nuovo
    2.63
    睃
    2.56
     exceedingly
    2.56
     lmao
    2.55
     ทำ
    2.50
     😊
    2.48
    Activations Density 0.003%

    No Known Activations