© 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. 48273
    Prev
    Next
    INDEX
    Explanations

    disclosure or categories

    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
     내가
    0.51
     زمان
    0.50
    馇
    0.49
     timpul
    0.48
    蛔
    0.47
    también
    0.46
    मंदिर
    0.45
    <unused954>
    0.45
    iyorum
    0.44
     tanıml
    0.44
    POSITIVE LOGITS
     schoon
    0.49
    褪
    0.46
     cleanup
    0.45
     Flücht
    0.44
     disclosure
    0.44
     Cleanup
    0.43
     Ž
    0.43
    eroy
    0.42
     disclosed
    0.42
     respirator
    0.42
    Activations Density 0.001%

    No Known Activations