© 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. 11815
    Prev
    Next
    INDEX
    Explanations

    medical advice or company financials

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

    The neuron is detecting e-commerce/product listing content (e.g. “Added to cart,” product names, prices, supplier details).

    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
    arrivalTime
    0.70
    <eos>
    0.66
    ↵
    0.66
    peers
    0.66
    peaks
    0.65
    际
    0.60
    ↵↵
    0.60
    とその
    0.60
    ŝ
    0.60
    在意
    0.59
    POSITIVE LOGITS
     ».
    0.91
     |.
    0.88
    ;.
    0.78
     Jul
    0.77
     ·
    0.76
     Posted
    0.76
     -.
    0.75
     +.
    0.73
     ‎
    0.72
     ”.
    0.71
    Activations Density 1.325%

    No Known Activations