© 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. 252378
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    al
    0.44
    dater
    0.43
    </th>
    0.42
    _{
    0.41
    ான
    0.41
    tering
    0.40
     را
    0.40
     महत्
    0.40
    介紹
    0.39
    tau
    0.38
    POSITIVE LOGITS
     Cambodia
    0.50
     CHP
    0.47
     Chinatown
    0.46
     Edna
    0.46
     coch
    0.46
     Echin
    0.46
    沏
    0.46
     Tottenham
    0.45
     masculinity
    0.45
     जै
    0.44
    Activations Density 0.002%

    No Known Activations