© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47768
    Prev
    Next
    INDEX
    Explanations

    customs and border protection

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

    The neuron strongly activates on numeric expressions—digits, quantities, and monetary or percentage amounts.

    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
     barriga
    -0.72
    adır
    -0.72
    idual
    -0.68
     шабло
    -0.68
     toe
    -0.68
     koe
    -0.67
     healing
    -0.66
     Arte
    -0.66
    allocator
    -0.66
    GHI
    -0.65
    POSITIVE LOGITS
     customs
    5.94
     Customs
    5.31
    Customs
    4.88
    custom
    3.97
     custom
    3.58
     Custom
    3.55
    CUSTOM
    3.41
     CUSTOM
    3.36
    Custom
    3.17
     тамо
    3.11
    Activations Density 0.046%

    No Known Activations