© 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. 259036
    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
     হই
    0.46
     ļ
    0.46
    닛
    0.44
    녀
    0.44
     برگزاری
    0.43
    üğ
    0.41
    놔
    0.41
     broadcasts
    0.40
     Wembley
    0.39
    лимпиа
    0.39
    POSITIVE LOGITS
     teilen
    0.51
    飩
    0.48
    теле
    0.46
    сцю
    0.45
    Bottom
    0.45
    валися
    0.45
     Einfluss
    0.44
     بالن
    0.44
    EndY
    0.44
     гли
    0.43
    Activations Density 0.001%

    No Known Activations