© 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. 110937
    Prev
    Next
    INDEX
    Explanations

    canvas

    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
     hydrologic
    -0.80
     漫
    -0.73
    кури
    -0.71
     physiologic
    -0.71
    Guatemala
    -0.70
    ticky
    -0.69
    箭头
    -0.68
    Dios
    -0.66
     הַ
    -0.65
     λογ
    -0.65
    POSITIVE LOGITS
     canvas
    4.97
    canvas
    4.28
     Canvas
    4.03
     canvases
    3.72
    Canvas
    3.72
     canvass
    2.94
     canv
    2.78
    キャン
    2.14
     хол
    1.99
    캔
    1.73
    Activations Density 0.048%

    No Known Activations