© 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. 107011
    Prev
    Next
    INDEX
    Explanations

    taxes and tariffs

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

    The neuron is principally detecting numeric tokens—especially monetary amounts, percentages, and other figures (often in tax or rate contexts).

    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
    merkung
    -0.92
    صفات
    -0.92
     །
    -0.88
    testng
    -0.85
    álise
    -0.82
    做出
    -0.82
     улуч
    -0.82
     fornecer
    -0.81
     Angebote
    -0.81
    GetX
    -0.80
    POSITIVE LOGITS
     levied
    2.41
     levy
    1.92
     taxes
    1.92
     collected
    1.83
     tax
    1.81
     imposition
    1.81
     Collected
    1.72
     levies
    1.71
     taxing
    1.71
     imposed
    1.71
    Activations Density 0.037%

    No Known Activations