© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48065
    Prev
    Next
    INDEX
    Explanations

    popular choices and classics

    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_31_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
     हात
    0.42
    iting
    0.41
    取り付け
    0.39
    嫌
    0.39
    missing
    0.39
    few
    0.39
     FontFamily
    0.39
    agger
    0.39
     ،
    0.38
     consigui
    0.38
    POSITIVE LOGITS
    귄
    0.44
    โยชน์
    0.43
     belts
    0.43
     endowments
    0.42
    WEST
    0.41
    EMP
    0.41
    ギフト
    0.41
    ALLE
    0.41
    HIST
    0.41
     unem
    0.39
    Activations Density 0.001%

    No Known Activations