© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18918
    Prev
    Next
    INDEX
    Explanations

    applying paint or coatings

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

    paint application and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⌊
    0.45
    ścio
    0.42
     維
    0.42
     obnov
    0.42
     inscri
    0.41
    磚
    0.41
    聾
    0.41
     importe
    0.41
    HomePage
    0.40
    ⎮
    0.40
    POSITIVE LOGITS
     paint
    0.87
    painter
    0.84
    paint
    0.82
     Paint
    0.82
    Paint
    0.81
     painters
    0.80
     Painters
    0.77
     painter
    0.77
     Painting
    0.73
     painting
    0.73
    Activations Density 0.104%

    No Known Activations