© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38858
    Prev
    Next
    INDEX
    Explanations

    afford to make a purchase

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

    The neuron flags terms and phrases related to money and financial transactions (costs, payments, investments, funds, prices, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     wurde
    -0.87
     Measurements
    -0.86
     Profits
    -0.84
     preocupado
    -0.82
    uetas
    -0.81
    vian
    -0.81
    Вт
    -0.80
    ₗ
    -0.79
    tonsoft
    -0.79
    Quest
    -0.79
    POSITIVE LOGITS
     expensive
    1.63
     costly
    1.23
     expenses
    1.23
     costs
    1.20
     purchase
    1.15
     purchasing
    1.13
     buy
    1.10
     membeli
    1.09
     buys
    1.09
     resources
    1.05
    Activations Density 0.053%

    No Known Activations