© 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. 112201
    Prev
    Next
    INDEX
    Explanations

    custom drawing and programming UI elements

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

    technical terms related to visual rendering, drawing, and styling in programming and document formatting contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code‐style identifiers—especially API method, property, or parameter names (e.g. “EnableVisualStyles,” “CompatibleTextRendering,” “Buttons,” “indent,” “sep,” “reset”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     první
    -1.83
     penggunaan
    -1.55
    !!!"
    -1.54
     empleos
    -1.52
     debilidad
    -1.51
    ！"
    -1.49
     rempliss
    -1.49
     privind
    -1.48
    !!"
    -1.48
     améli
    -1.45
    POSITIVE LOGITS
     to
    1.95
    ;
    1.94
     for
    1.62
     in
    1.61
    ’
    1.51
     like
    1.49
     awakeFromNib
    1.44
    4
    1.38
    0
    1.33
    //});
    1.32
    Activations Density 0.001%

    No Known Activations