© 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. 97838
    Prev
    Next
    INDEX
    Explanations

    tax planning

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

    The neuron fires strongly on tax-related terms (like “tax,” “taxes,” “tax planning,” “Child Tax Credit,” etc.) and associated numeric or financial references.

    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
     prijs
    -0.95
     сутки
    -0.89
    缭
    -0.88
     cartel
    -0.87
     prezzo
    -0.84
     DEMAND
    -0.84
     aggiungere
    -0.82
     DAILY
    -0.79
    enus
    -0.79
    ctivos
    -0.79
    POSITIVE LOGITS
     tax
    2.25
     Tax
    1.80
     taxes
    1.78
     filing
    1.72
     IRS
    1.65
    Tax
    1.64
    tax
    1.55
     taxable
    1.45
     налого
    1.41
     income
    1.34
    Activations Density 0.048%

    No Known Activations