© 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. 33809
    Prev
    Next
    INDEX
    Explanations

    airport security and immigration

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

    The neuron strongly activates on words describing airport‐related infrastructure and procedures (e.g. airport, line/queue, check-in, baggage).

    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
     risotto
    -0.74
     enshr
    -0.73
    +"&
    -0.71
    ://
    -0.71
    цах
    -0.69
     quán
    -0.69
     unreachable
    -0.69
     nears
    -0.68
    cen
    -0.68
    甙
    -0.68
    POSITIVE LOGITS
     immigration
    2.67
     Immigration
    2.31
    immigration
    2.20
     customs
    2.19
    Immigration
    2.05
     Customs
    1.82
    Customs
    1.79
     clearance
    1.54
     security
    1.54
     passport
    1.48
    Activations Density 0.026%

    No Known Activations