© 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. 72173
    Prev
    Next
    INDEX
    Explanations

    Hong Kong and related places

    np_acts-logits-general · gemini-2.5-flash-lite

    Hong Kong, HK, Cantonese, Kowloon

    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
    烀
    0.59
    岨
    0.55
     dată
    0.55
    輥
    0.51
    狍
    0.51
    疖
    0.49
    苾
    0.47
    Ꮑ
    0.47
     கெல்வின்
    0.46
     rougeâtre
    0.46
    POSITIVE LOGITS
     Hong
    1.44
     HK
    1.41
     Hongkong
    1.37
    香港
    1.35
    Hong
    1.34
    HK
    1.27
     Kowloon
    1.22
     hk
    1.11
     香港
    1.11
     Cantonese
    1.09
    Activations Density 0.083%

    No Known Activations