© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8364
    Prev
    Next
    INDEX
    Explanations

    cannabis product packaging and regulation

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

    The neuron strongly activates on words referring to cannabis (e.g., hemp, marijuana, CBD, cannabis) and related plant terminology.

    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
     ferrite
    0.69
     ITable
    0.68
     Kidney
    0.64
     Уен
    0.61
     अंडे
    0.59
     Phosphate
    0.59
    svn
    0.58
    鯵
    0.58
     Selenium
    0.57
     الحاس
    0.57
    POSITIVE LOGITS
     cannabis
    2.41
     cannab
    2.14
     Cannabis
    2.14
     hemp
    2.08
     marijuana
    2.06
     cannabin
    2.05
     cannabinoids
    1.95
     CBD
    1.94
    CBD
    1.90
     THC
    1.88
    Activations Density 0.204%

    No Known Activations