© 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. 84097
    Prev
    Next
    INDEX
    Explanations

    canvas and fabric materials

    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
     Stein
    -0.77
    APPEND
    -0.71
    enscha
    -0.70
    ディガン
    -0.69
    гию
    -0.69
     gustar
    -0.69
    addObject
    -0.68
     Fur
    -0.68
    计算机
    -0.68
     Silk
    -0.67
    POSITIVE LOGITS
     canvas
    2.95
     Canvas
    2.39
    canvas
    2.30
    Canvas
    2.17
     canvass
    1.85
     canvases
    1.61
     cloth
    1.54
     canv
    1.48
     Leinwand
    1.42
     burlap
    1.41
    Activations Density 0.043%

    No Known Activations