© 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. 12922
    Prev
    Next
    INDEX
    Explanations

    Thailand and Thai places

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

    Thailand and Thai 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_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
     소련
    0.54
     Newfoundland
    0.50
    加拿大
    0.50
    苏联
    0.49
     নিউইয়
    0.48
    爆发
    0.48
     কানা
    0.48
    纽
    0.48
    北美
    0.48
     न्यूयॉर्क
    0.48
    POSITIVE LOGITS
     Thai
    1.68
     Bangkok
    1.68
    Thai
    1.64
     Thailand
    1.59
    Thailand
    1.59
     thailand
    1.40
    泰国
    1.38
     Phuket
    1.25
     thai
    1.22
     Pattaya
    1.22
    Activations Density 0.168%

    No Known Activations