© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 49215
    Prev
    Next
    INDEX
    Explanations

    geometric concepts and shapes

    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/layer_53_width_262k_l0_medium
    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
    تميز
    0.43
     direction
    0.40
    کل
    0.40
    legal
    0.39
     convective
    0.39
    grained
    0.39
    Kaw
    0.39
    ¿
    0.38
     endings
    0.38
    conduct
    0.38
    POSITIVE LOGITS
     shapes
    0.81
    shapes
    0.79
     Shapes
    0.77
     геометри
    0.73
     도형
    0.72
     Geometric
    0.71
    Geometric
    0.70
     фигуры
    0.69
     geometric
    0.67
    Shapes
    0.65
    Activations Density 0.004%

    No Known Activations