© 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. 75963
    Prev
    Next
    INDEX
    Explanations

    payment options and renewal

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

    The neuron fires on marketing/payment-related calls to action—phrases offering purchase/payment options (e.g. “Own it!”, “Buy Now Pay Later,” “within 15 minutes”) with exclamation emphasis.

    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
    薬
    -0.72
     ostra
    -0.71
    ⑸
    -0.70
     xvii
    -0.69
    浪费
    -0.68
    bowler
    -0.68
    shutil
    -0.68
     Matisse
    -0.68
    烷
    -0.68
     rx
    -0.67
    POSITIVE LOGITS
     payment
    3.38
     Payment
    2.72
     payments
    2.69
    Payment
    2.63
    payment
    2.59
     installment
    2.31
     installments
    2.08
    PAYMENT
    2.06
     PAYMENT
    2.05
     Payments
    2.03
    Activations Density 0.027%

    No Known Activations