© 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. 34-GEMMASCOPE-RES-131K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    prepaid and debit card terms

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

    The neuron strongly activates on capitalized commercial or product names—especially financial service brands (e.g. prepaid cards, banks, MasterCard) and other trademarked terms.

    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
    isatie
    -0.76
    béco
    -0.76
    💤
    -0.73
    ביר
    -0.73
    ਟ
    -0.72
    نس
    -0.70
    iuo
    -0.70
     γυναι
    -0.69
     Rogan
    -0.69
     PROFES
    -0.69
    POSITIVE LOGITS
     prepaid
    1.98
     reload
    1.96
    reload
    1.75
     Prepaid
    1.61
    Reload
    1.52
     Reload
    1.42
     pre
    1.41
     reloading
    1.30
     loaded
    1.29
     loading
    1.25
    Activations Density 0.019%

    No Known Activations