© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92648
    Prev
    Next
    INDEX
    Explanations

    USDA agriculture and rural development

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

    This neuron activates on numeric tokens (numbers or number-containing strings).

    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
    ***/
    -0.83
    🚴
    -0.77
    насти
    -0.77
    routeProvider
    -0.75
    ="[
    -0.71
    !***
    -0.71
     ویکی‌پدیای
    -0.69
    plet
    -0.69
    IActionResult
    -0.69
    writel
    -0.68
    POSITIVE LOGITS
     USDA
    3.14
    USDA
    2.64
    usda
    1.49
     ARS
    1.29
    APH
    1.26
     Agriculture
    1.16
    Agriculture
    1.05
     وزارة
    0.96
     وزارت
    0.96
     Rural
    0.94
    Activations Density 0.020%

    No Known Activations