© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10047
    Prev
    Next
    INDEX
    Explanations

    This neuron detects terminology related to payment processing and booking/payment forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words related to financial transactions, business services, and commercial offerings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words containing the morpheme “ment,” especially -ment suffixed forms.

    oai_token-act-pair · gpt-5Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ствен
    0.69
    ственно
    0.65
     अंश
    0.62
     puls
    0.59
    puls
    0.59
     intim
    0.57
     CBC
    0.57
     মিনিট
    0.57
     Pos
    0.57
    новение
    0.57
    POSITIVE LOGITS
    alist
    0.89
    um
    0.82
    Xpaths
    0.82
    arians
    0.78
    ARY
    0.77
    arian
    0.72
    UM
    0.71
    álně
    0.70
    alnya
    0.68
    ary
    0.68
    Activations Density 0.552%

    No Known Activations