© 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. 59043
    Prev
    Next
    INDEX
    Explanations

    incurring financial costs or expenses

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

    The main thing this neuron does is pick out words having to do with costs, expenses, or expenditures.

    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
    верен
    -0.76
    ждународ
    -0.75
    corpion
    -0.73
     vejo
    -0.71
     vinaigrette
    -0.69
    celer
    -0.67
     mempengaruhi
    -0.67
     Doi
    -0.66
    風味
    -0.64
    ᶦ
    -0.64
    POSITIVE LOGITS
     incur
    4.38
     incurred
    4.03
     incurring
    3.86
     bear
    1.92
     suffered
    1.71
    Bear
    1.61
     bears
    1.61
     incursion
    1.60
     costs
    1.51
     suffer
    1.48
    Activations Density 0.042%

    No Known Activations