© 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. 10-GEMMASCOPE-RES-131K
    4. 104408
    Prev
    Next
    INDEX
    Explanations

    expatriate or exiled people

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

    The neuron activates on terms referring to people living outside their home country—e.g. “expat,” “expatriate,” or “diaspora.”

    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
    をしていた
    -1.96
    しなかった
    -1.94
    轳
    -1.93
     parecer
    -1.91
     piden
    -1.87
    紧接着
    -1.78
    されてる
    -1.78
     celebrate
    -1.77
     refine
    -1.73
     solicitar
    -1.73
    POSITIVE LOGITS
    ’
    2.59
    ’,
    2.17
    नलोड
    1.97
     bunda
    1.96
    geſ
    1.94
     komik
    1.93
     hins
    1.86
     yake
    1.84
     jure
    1.82
    镦
    1.80
    Activations Density 0.008%

    No Known Activations