© 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. 13511
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on nouns naming goods, services, food, or provisions—i.e. items or offerings being supplied or provided.

    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
     corneal
    0.61
     stator
    0.61
     रथ
    0.59
    十分に
    0.58
     كري
    0.57
     adenocarcinoma
    0.54
     Epilepsy
    0.54
    г
    0.54
     polytopes
    0.53
     dyslexia
    0.53
    POSITIVE LOGITS
     beverages
    1.06
     Beverages
    0.99
     boissons
    0.89
     beverage
    0.84
     condiments
    0.82
    drinks
    0.82
     Geträn
    0.82
     seasonings
    0.80
     bebidas
    0.80
     पेय
    0.79
    Activations Density 0.584%

    No Known Activations