© 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. 34-GEMMASCOPE-RES-131K
    4. 83750
    Prev
    Next
    INDEX
    Explanations

    Customs and border crossings

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

    The neuron detects references to official enforcement and border‐control terminology.

    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
    william
    -0.73
    EPS
    -0.73
     đàn
    -0.70
     unsteady
    -0.69
    ाद
    -0.69
     ngọt
    -0.69
    Jegyzőkönyv
    -0.69
    getBean
    -0.68
     commissioning
    -0.68
     Pradhan
    -0.68
    POSITIVE LOGITS
     NEX
    1.08
     Cana
    0.90
    Cana
    0.85
    Canada
    0.81
     Canada
    0.81
     America
    0.79
    zzano
    0.78
    trusted
    0.77
     Fas
    0.77
     crossing
    0.76
    Activations Density 0.025%

    No Known Activations