© 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. 10-GEMMASCOPE-RES-131K
    7. 20316
    Prev
    Next
    INDEX
    Explanations

    paying for

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

    The neuron flags mentions of paying for or funding something—that is, “for” in contexts of monetary transactions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    [
    -2.03
    est
    -1.92
    </b>
    -1.77
     governs
    -1.73
    -1.73
     localizado
    -1.69
    '
    -1.67
     proviene
    -1.66
     him
    -1.66
    “
    -1.66
    POSITIVE LOGITS
    沨
    1.88
     дорогой
    1.83
     yanında
    1.66
    𓆜
    1.66
    pentru
    1.64
     cải
    1.63
    ísticos
    1.63
    保湿
    1.61
    分からない
    1.60
    palabras
    1.60
    Activations Density 0.011%
    No Known Activations