© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    interest on payments or income

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

    This neuron fires on commercial call-to-action or promotional phrases that promise immediacy or instant service, such as “Instant Download,” “Get Instant Access,” and similar marketing offers.

    oai_token-act-pair · o4-miniTriggered 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
    印刷
    0.61
    (@"
    0.58
    শাখ
    0.56
    ག
    0.54
    回来
    0.54
    sourceFolder
    0.54
    StateToProps
    0.54
    reward
    0.53
    맹
    0.53
     repay
    0.52
    POSITIVE LOGITS
    वर्ड
    0.57
     지나
    0.55
     가능한
    0.54
     บ้าน
    0.54
     inclinations
    0.53
     אטאטורק
    0.53
     입니다
    0.52
     bied
    0.52
     Partner
    0.52
     ಸಮ
    0.52
    Activations Density 0.000%

    No Known Activations