© 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. 81025
    Prev
    Next
    INDEX
    Explanations

    tax exemption and deductions

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

    The neuron strongly activates on numeric tokens and financial‐tax terminology—i.e. numbers, dollar amounts, tax rates, and related monetary figures.

    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
     cuánt
    -0.81
    GUY
    -0.79
     اط
    -0.77
    certs
    -0.76
     tubes
    -0.76
    付
    -0.75
     réaliste
    -0.75
     Alten
    -0.73
    paghetti
    -0.73
    irsten
    -0.72
    POSITIVE LOGITS
     exemptions
    2.28
     exemption
    2.20
     Exemption
    1.59
     deductions
    1.57
     claimed
    1.45
     deduction
    1.32
     claiming
    1.29
    emptions
    1.27
     exempt
    1.24
     homestead
    1.23
    Activations Density 0.029%

    No Known Activations