© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17236
    Prev
    Next
    INDEX
    Explanations

    border customs and entry

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

    customs and border procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    结
    0.61
    建筑
    0.52
     öğret
    0.51
    结婚
    0.50
    写作
    0.49
    瓴
    0.48
     വേദ
    0.48
    涧
    0.47
     algéb
    0.47
     métier
    0.47
    POSITIVE LOGITS
     Customs
    1.14
    入境
    1.06
     customs
    1.04
     border
    1.02
     Border
    0.99
    border
    0.98
     smuggling
    0.98
    Border
    0.89
     smugglers
    0.89
    BORDER
    0.88
    Activations Density 0.109%

    No Known Activations