© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4401
    Prev
    Next
    INDEX
    Explanations

    color, hue, coloring

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

    hex color

    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_53_width_65k_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
     weit
    0.48
     langt
    0.46
     ደቂ
    0.40
    ද්ග
    0.38
    ূনতম
    0.38
    symplectic
    0.38
    ನಾಟಕ
    0.37
    癶
    0.36
     जुर्मा
    0.36
    etli
    0.36
    POSITIVE LOGITS
     color
    4.50
     colour
    4.34
    color
    4.19
     colors
    4.16
     Color
    4.03
     رنگ
    4.03
    颜色
    3.98
     colours
    3.97
     Colour
    3.91
     COLOR
    3.91
    Activations Density 0.528%

    No Known Activations