© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116388
    Prev
    Next
    INDEX
    Explanations

    Customs Border Protection Enforcement

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

    The neuron fires strongly on the formal mention of “U.S. Customs and Border Protection” (and closely related official attributions).

    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
    épendance
    -0.81
    mêmes
    -0.73
     studied
    -0.71
     sacrificed
    -0.71
    Blockly
    -0.70
    μμ
    -0.70
     Kod
    -0.69
     Rapp
    -0.69
    消除
    -0.69
    Rapp
    -0.69
    POSITIVE LOGITS
     Customs
    1.38
     customs
    1.24
    Customs
    1.22
     ICE
    1.16
     detainees
    1.14
     detention
    1.08
     Border
    1.05
    CUSTOM
    1.05
     agents
    1.03
    ICE
    1.01
    Activations Density 0.031%

    No Known Activations