© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 61645
    Prev
    Next
    INDEX
    Explanations

    brushstrokes or brush painting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erv
    0.46
     whit
    0.42
    ode
    0.41
    oy
    0.41
     joy
    0.41
    yst
    0.40
    array
    0.40
    ẩ
    0.40
     joyful
    0.39
    hyd
    0.38
    POSITIVE LOGITS
     Brush
    0.80
     brush
    0.74
    Brush
    0.72
    刷
    0.67
     brushes
    0.67
     brushed
    0.66
    brush
    0.64
     brushing
    0.59
     ब्रश
    0.59
    strokes
    0.58
    Activations Density 0.001%

    No Known Activations