© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6504
    Prev
    Next
    INDEX
    Explanations

    search terms for specific items or services

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

    The neuron activates on numeric expressions tied to drug information—e.g. doses, prices, or strengths of pharmaceutical products.

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

    spam content related to pharmaceutical products and online sales.

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

    mentions of pharmaceuticals and online drug sales, especially references to dosages, prices, prescriptions, and purchasing information for medications.

    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
     Essay
    0.64
     Ubuy
    0.64
     निबंध
    0.62
     essay
    0.60
    ್ಟ
    0.57
     Cannabis
    0.55
    <unused49>
    0.54
     [/
    0.54
     บริษัท
    0.54
    ப்பதை
    0.54
    POSITIVE LOGITS
    瞔
    0.55
     ಹಾಕ
    0.54
     afterthought
    0.54
    ญาต
    0.53
    故事
    0.51
    ))\
    0.50
     posle
    0.50
     vorige
    0.50
    長さ
    0.49
     verstehen
    0.49
    Activations Density 0.085%

    No Known Activations