© 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. 22-GEMMASCOPE-RES-131K
    7. 36482
    Prev
    Next
    INDEX
    Explanations

    expats abroad, diaspora communities

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

    The neuron activates on mentions of expatriate or diaspora communities (e.g. “expats,” “expatriate,” specific countries or cities in the context of an ethnic‐community magazine or group”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     today
    -1.08
     animal
    -1.02
     aasta
    -0.97
     a
    -0.95
     you
    -0.94
     entraîne
    -0.94
     todas
    -0.94
    取り組
    -0.93
    契約
    -0.93
     الرحمن
    -0.92
    POSITIVE LOGITS
     diaspora
    1.38
     remittances
    1.14
     pimpinan
    1.13
     expatri
    1.12
     pengurus
    1.09
     ratusan
    1.07
     Jedes
    1.06
     emig
    1.06
     sesama
    1.05
    🇺🇸
    1.05
    Activations Density 0.058%

    No Known Activations