© 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. 48136
    Prev
    Next
    INDEX
    Explanations

    tax related transactions

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

    This neuron detects numeric expressions attached to tax- or duty-related terms (e.g., rates, levies, duties).

    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
    وده
    -0.88
     neigh
    -0.84
     contender
    -0.83
     vicini
    -0.82
    娜
    -0.81
    Dermal
    -0.79
    ůli
    -0.79
    墘
    -0.79
     possib
    -0.78
     trebu
    -0.78
    POSITIVE LOGITS
     transactions
    1.13
     corporations
    1.03
     certain
    1.01
     purchases
    0.96
     transfers
    0.95
     those
    0.94
     every
    0.92
     cigarettes
    0.92
    Ө
    0.92
     imports
    0.91
    Activations Density 0.018%

    No Known Activations