© 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. 75107
    Prev
    Next
    INDEX
    Explanations

    drawing operations

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

    This neuron spots occurrences of “draw” (especially “draw()”) in code snippets.

    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
    ’
    -1.95
    .”
    -1.86
    w
    -1.68
    up
    -1.65
    S
    -1.63
    eaked
    -1.62
    A
    -1.62
     verschiedene
    -1.56
    graphy
    -1.53
    s
    -1.53
    POSITIVE LOGITS
     Affaires
    1.70
    från
    1.70
     verheir
    1.70
    ēj
    1.66
     folha
    1.63
    dekor
    1.59
    dáms
    1.58
    ajuste
    1.52
    boneca
    1.50
     murale
    1.49
    Activations Density 0.014%

    No Known Activations