© 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. 115915
    Prev
    Next
    INDEX
    Explanations

    deportation and immigration enforcement

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

    This neuron identifies tokens in formal legal-document headers—uppercase names, docket numbers, court names, and other structural metadata.

    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
    ensiva
    -0.81
    ޖ
    -0.74
     paralysis
    -0.74
    htiö
    -0.73
    <0xB7>
    -0.73
     boycott
    -0.72
     ouverture
    -0.71
     layout
    -0.70
     ಮಾ
    -0.69
     approvals
    -0.69
    POSITIVE LOGITS
     deportation
    2.44
     deport
    2.16
     deported
    2.00
     expulsion
    1.44
     deporte
    1.38
     depor
    1.34
     expel
    1.31
     immigration
    1.30
     repatri
    1.27
     expelled
    1.20
    Activations Density 0.035%

    No Known Activations