© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 356
    Prev
    Next
    INDEX
    Explanations

    Vietnamese destinations

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

    Vietnamese and Vietnam

    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_53_width_65k_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
    ўцаў
    0.64
    ўкі
    0.63
     Расійскай
    0.57
     гульнявыя
    0.55
    цыю
    0.54
    ϙ
    0.54
    髌
    0.53
    блі
    0.53
    ნა
    0.53
    猀
    0.53
    POSITIVE LOGITS
     Vietnamese
    1.80
     Việt
    1.70
     Vietnam
    1.68
    Viet
    1.64
     Viet
    1.63
     Hanoi
    1.59
     Thanh
    1.59
     Nguyễn
    1.58
    Vietnam
    1.48
     Saigon
    1.48
    Activations Density 0.127%

    No Known Activations