© 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. 26975
    Prev
    Next
    INDEX
    Explanations

    sharpness and brightness

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

    shininess and brilliance of surfaces

    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
     apolog
    0.56
    の時間
    0.56
    的形式
    0.55
     (
    0.54
    ebab
    0.54
     tatha
    0.54
    的相关
    0.54
    ggak
    0.53
    bub
    0.53
    的用户
    0.53
    POSITIVE LOGITS
     sharpen
    0.88
     brilh
    0.88
    鋭
    0.86
     sharpness
    0.83
    闪
    0.83
     चमक
    0.82
     चमकदार
    0.82
     sharper
    0.81
     sharpened
    0.80
    锃
    0.80
    Activations Density 0.088%

    No Known Activations