© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47733
    Prev
    Next
    INDEX
    Explanations

    drawing and rendering visuals

    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
     gespeichert
    -0.84
    アレル
    -0.84
     lexic
    -0.79
     ICO
    -0.78
     objectForKey
    -0.75
     gyhoeddwyd
    -0.74
    linearGradient
    -0.73
     daisy
    -0.73
    Conce
    -0.72
     detalló
    -0.72
    POSITIVE LOGITS
     canvas
    1.62
    canvas
    1.45
     preview
    1.38
    Canvas
    1.38
     drawing
    1.37
     Canvas
    1.17
    Preview
    1.16
    preview
    1.13
     Drawing
    1.12
     visualization
    1.11
    Activations Density 0.070%

    No Known Activations