© 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. 78865
    Prev
    Next
    INDEX
    Explanations

    fees, charges, taxes, costs

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

    The neuron is detecting terms related to monetary costs and charges—words like taxes, fees, levies, charges, costs, and refunds.

    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
     Ogle
    -0.80
    恭
    -0.79
     drastically
    -0.77
    ئة
    -0.76
     sexta
    -0.73
     dramatically
    -0.73
     nobile
    -0.73
     corresponding
    -0.72
     valida
    -0.72
     Giant
    -0.71
    POSITIVE LOGITS
     fees
    2.34
     charges
    2.13
     taxes
    1.80
    fees
    1.73
    Fees
    1.70
    charges
    1.68
     Fees
    1.64
    Charges
    1.59
     Charges
    1.54
     costs
    1.43
    Activations Density 0.028%

    No Known Activations