© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81358
    Prev
    Next
    INDEX
    Explanations

    Thailand and Thai words

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

    The neuron is highly responsive to mentions of Thailand or Thai-related entities (e.g., “Thai,” “Thailand,” and Thai organization or place names”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     แท้
    -1.23
     กล่อง
    -1.13
     การ์ตูน
    -1.13
     ลาย
    -1.08
     Thần
    -1.01
     สาว
    -1.01
     เสื้อ
    -0.98
     Lengkap
    -0.98
     วาด
    -0.97
    吧
    -0.92
    POSITIVE LOGITS
     Thailand
    2.34
     Thai
    2.30
     Bangkok
    2.27
    Thai
    2.13
    Thailand
    2.11
    Bangkok
    1.88
     Pattaya
    1.69
     Phuket
    1.63
    thai
    1.62
     thai
    1.52
    Activations Density 0.102%

    No Known Activations