© 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. 7272
    Prev
    Next
    INDEX
    Explanations

    supplements pills gummies capsules

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

    The neuron is keyed to mentions of the weight‐loss supplement “Garcinia Cambogia” (e.g. firing strongly on its brand/name tokens).

    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
     unix
    0.59
    unix
    0.58
     tax
    0.57
     kines
    0.57
     reproducible
    0.55
    郗
    0.55
    沣
    0.54
    鎳
    0.52
     landscape
    0.52
     baroque
    0.52
    POSITIVE LOGITS
     Gummies
    1.04
     Reviews
    0.93
     CBD
    0.91
     gummies
    0.88
    CBD
    0.86
     Cbd
    0.81
     Pills
    0.79
    Reviews
    0.78
     Keto
    0.76
     Ingredients
    0.72
    Activations Density 0.115%

    No Known Activations