© 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. 15804
    Prev
    Next
    INDEX
    Explanations

    shapes and colors

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

    drawing shapes and colors

    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
     ممن
    0.49
     आपदा
    0.48
    祸
    0.48
     unlawful
    0.47
     konflik
    0.47
     problemen
    0.47
    टरीना
    0.46
     irrevoc
    0.46
     ಸಮಸ್ಯೆ
    0.46
    谋
    0.45
    POSITIVE LOGITS
     oval
    0.77
     color
    0.70
     diameters
    0.68
     Diameter
    0.68
    color
    0.67
     shapes
    0.67
     diameter
    0.66
     circles
    0.65
     ellipse
    0.64
     Shapes
    0.64
    Activations Density 0.006%

    No Known Activations