© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41324
    Prev
    Next
    INDEX
    Explanations

    Thai places and history

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

    The neuron primarily detects mentions of Thai geographic names and related proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ៚
    -1.88
    𖣘
    -1.63
    
    -1.52
    艫
    -1.46
     miliki
    -1.42
     Mexicano
    -1.39
    鐒
    -1.38
    鏝
    -1.36
     censi
    -1.36
    ༆
    -1.35
    POSITIVE LOGITS
    \
    1.55
     are
    1.38
     (
    1.30
    SuccessListener
    1.27
     ночи
    1.26
     for
    1.24
     as
    1.23
     ontwerp
    1.22
     pertain
    1.22
     originally
    1.21
    Activations Density 0.006%

    No Known Activations