© 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. 65330
    Prev
    Next
    INDEX
    Explanations

    international student visas

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

    The neuron fires on visa category codes (e.g. OPT, F-1, H-1B) and similar uppercase visa/status abbreviations.

    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
     ingat
    -0.85
     Māori
    -0.81
    公司
    -0.73
    inkscape
    -0.71
     verst
    -0.71
     nisk
    -0.71
     lipat
    -0.71
    КС
    -0.70
    Jud
    -0.68
    🚚
    -0.68
    POSITIVE LOGITS
     visa
    1.42
     immigration
    1.23
    immigration
    1.22
     international
    1.20
     Immigration
    1.19
     students
    1.10
     visas
    1.10
    international
    1.06
    国際
    1.05
    Visa
    1.05
    Activations Density 0.009%

    No Known Activations