© 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. 34-GEMMASCOPE-RES-131K
    7. 7189
    Prev
    Next
    INDEX
    Explanations

    mainland/continental US China

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

    The neuron activates on the key function words (articles, prepositions, and directional terms) used in geographic location descriptions.

    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
     kuan
    -0.73
     Marines
    -0.69
    axy
    -0.69
     lembrar
    -0.69
     وہ
    -0.68
    ProgressDialog
    -0.68
     초기
    -0.68
    🈺
    -0.66
    证明
    -0.66
     coincidence
    -0.66
    POSITIVE LOGITS
     mainland
    5.28
     Mainland
    3.36
     continental
    2.61
    大陆
    2.52
    大陸
    2.11
     continente
    2.08
     continent
    1.99
    continental
    1.97
     Continental
    1.96
    本土
    1.94
    Activations Density 0.038%

    No Known Activations