© 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. 34-GEMMASCOPE-RES-131K
    7. 60306
    Prev
    Next
    INDEX
    Explanations

    drawing and graphics operations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ResponseModel
    -0.76
    Interpolator
    -0.73
    ঘ
    -0.72
    笺
    -0.70
    brale
    -0.69
    DaoImpl
    -0.69
    Gao
    -0.68
    🗼
    -0.68
    Giá
    -0.68
    égories
    -0.68
    POSITIVE LOGITS
     draw
    1.50
     Draw
    1.38
    draw
    1.19
    Draw
    1.17
     primitive
    1.13
     drawing
    1.13
    degenerate
    1.12
    Primitive
    1.07
    primitive
    1.05
     strip
    1.01
    Activations Density 0.019%

    No Known Activations