© 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. 34-GEMMASCOPE-RES-131K
    7. 58674
    Prev
    Next
    INDEX
    Explanations

    drawing

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

    The neuron strongly activates on occurrences of the word “Drawing,” typically in import or namespace references (e.g. System.Drawing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    dure
    -0.92
    chtest
    -0.82
    piring
    -0.82
    
    -0.76
     mitz
    -0.75
     znak
    -0.74
    蝠
    -0.73
    Employer
    -0.73
    𝕛
    -0.72
    resa
    -0.70
    POSITIVE LOGITS
     freuen
    0.74
    Auth
    0.69
    CV
    0.65
     трубы
    0.64
     delighted
    0.63
     dropped
    0.63
    ync
    0.63
     игры
    0.63
     contribute
    0.63
    PK
    0.63
    Activations Density 0.044%

    No Known Activations