© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23547
    Prev
    Next
    INDEX
    Explanations

    geometric shapes or layout commands

    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_40_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
    onavirus
    0.37
    ];
    0.37
    auml
    0.37
    function
    0.36
     minus
    0.36
    كمل
    0.36
    angling
    0.35
     function
    0.35
    coe
    0.35
    parameter
    0.35
    POSITIVE LOGITS
     보니
    0.40
    糍
    0.40
    питы
    0.39
    उद्योग
    0.39
     Казіно
    0.39
     Plains
    0.38
     सीटेट
    0.38
     planes
    0.38
     بنانے
    0.38
     Planes
    0.38
    Activations Density 0.000%

    No Known Activations