© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118677
    Prev
    Next
    INDEX
    Explanations

    money and transactions

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

    The neuron activates on language about money changing hands—payments, costs, and financial transactions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases related to spending, earning, or saving money.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to money and financial transactions, especially currency, payments, pricing, taxes, and monetary value

    oai_token-act-pair · gpt-5Triggered 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
    lys
    -0.84
     ör
    -0.84
    WriteString
    -0.79
    ೫
    -0.78
     matematika
    -0.78
     menores
    -0.77
    quear
    -0.77
     Stocks
    -0.77
     недели
    -0.76
    outils
    -0.75
    POSITIVE LOGITS
     dollars
    3.20
     dollar
    2.84
    dollar
    2.20
     bucks
    2.16
     Dollars
    2.11
    dollars
    2.00
     Dollar
    1.97
    Dollar
    1.88
     $$$
    1.87
     $$
    1.76
    Activations Density 0.050%

    No Known Activations