© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112008
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets

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

    repetitive line-by-line patterns in code or structured data files.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.91
    Тарих
    -1.90
    ſu
    -1.87
    JAMIN
    -1.77
    ☫
    -1.71
     glyphicon
    -1.70
    컹
    -1.69
     Scritto
    -1.67
    ⠀⠀⠀⠀
    -1.66
     quæ
    -1.66
    POSITIVE LOGITS
    b
    2.20
    k
    2.20
    g
    2.03
    h
    1.93
    ing
    1.93
    c
    1.91
    n
    1.91
    te
    1.90
    t
    1.80
    in
    1.78
    Activations Density 0.017%

    No Known Activations