© 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. 228907
    Prev
    Next
    INDEX
    Explanations

    language

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    تقدم
    0.46
     Lancashire
    0.44
    澜
    0.44
    强势
    0.43
     EARL
    0.43
     algebraically
    0.43
    تميز
    0.41
    %!
    0.40
    带动
    0.39
    "
    0.39
    POSITIVE LOGITS
    ם
    0.59
    ן
    0.55
     ashamed
    0.51
     של
    0.48
    レット
    0.46
    йки
    0.44
     Pengh
    0.44
    倣
    0.43
    の場合は
    0.43
     spongy
    0.43
    Activations Density 0.001%

    No Known Activations