© 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. 245573
    Prev
    Next
    INDEX
    Explanations

    Hong Kong Milk Tea

    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
    ة
    0.55
    ave
    0.47
    rets
    0.46
    ing
    0.45
    avgs
    0.45
    atts
    0.45
     vzh
    0.44
    انات
    0.43
    vary
    0.43
    biggr
    0.43
    POSITIVE LOGITS
     disparition
    0.53
     spieg
    0.51
    лта
    0.49
    붙
    0.47
     frequ
    0.45
     versi
    0.45
     корпус
    0.45
     decision
    0.44
    یکی
    0.44
     fő
    0.44
    Activations Density 0.001%

    No Known Activations