© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13751
    Prev
    Next
    INDEX
    Explanations

    card transactions and fraud

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

    The neuron flags numeric tokens and nearby words that denote monetary amounts (prices, fees, charges).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     आयुर्वेदिक
    0.68
     هفته
    0.66
     Администра
    0.64
     Scouting
    0.63
     Erfurt
    0.61
     trusses
    0.61
     оценка
    0.61
     direitos
    0.61
     डीएनए
    0.61
     鳥
    0.61
    POSITIVE LOGITS
     card
    1.93
    Card
    1.69
     Card
    1.66
    card
    1.64
     MasterCard
    1.63
     कार्ड
    1.58
    信用卡
    1.57
     cards
    1.56
    Cards
    1.52
    カード
    1.52
    Activations Density 0.448%

    No Known Activations