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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127997
    Prev
    Next
    INDEX
    Explanations

    immigration and emigration

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

    This neuron specializes in detecting tokens related to migration or immigration (e.g. “immig-,” “emigrated,” “immigration,” “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
    ()]);
    -1.95
    Of
    -1.73
    ();
    -1.73
    ि
    -1.70
    or
    -1.69
    ot
    -1.67
    ?"
    -1.64
    al
    -1.63
    Not
    -1.61
    ("/{
    -1.60
    POSITIVE LOGITS
    鲮
    2.19
    巂
    1.77
    跸
    1.77
    
    1.76
    ㌧
    1.63
     kalori
    1.61
    臏
    1.59
     souha
    1.59
     ſont
    1.57
    
    1.56
    Activations Density 0.029%

    No Known Activations