© 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-16K
    7. 12639
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

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

    Hong Kong, Ant Design, Cantonese, August, boasts

    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_16k_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
    0.63
    輥
    0.56
    狍
    0.55
    岨
    0.54
     dată
    0.53
     Akron
    0.53
    Ꮑ
    0.52
     rougeâtre
    0.51
    鳟
    0.50
    苾
    0.49
    POSITIVE LOGITS
     Hong
    1.59
     Hongkong
    1.55
     HK
    1.49
    香港
    1.45
    Hong
    1.43
     Kowloon
    1.34
    HK
    1.31
     Cantonese
    1.30
     hk
    1.20
     hong
    1.20
    Activations Density 0.116%

    No Known Activations