© 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. 254745
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    цыя
    0.57
    fohlen
    0.56
    鿢
    0.55
     وین
    0.54
    沺
    0.53
     Приступ
    0.53
    ൪
    0.52
    铯
    0.52
    鏻
    0.52
    讲述
    0.52
    POSITIVE LOGITS
     A
    0.55
     We
    0.54
     G
    0.49
    </h3>
    0.49
     V
    0.48
    <start_of_image>
    0.47
    </strong>
    0.46
    :
    0.46
    ’
    0.46
    am
    0.46
    Activations Density 0.000%

    No Known Activations