© 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. 7021
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens belonging to restaurant‐and‐food review contexts—e.g. chef names, menu items, culinary descriptors, hours of operation, and related proper nouns in a dining or hospitality setting.

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

    descriptive content about restaurants, food, and culinary experiences.

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

    mentions of food and drink, especially restaurant and bar-related content—chefs, menus, beverages, tasting/review notes, recipes, and operating hours/details.

    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
    🥤
    0.64
     ১৯৭১
    0.62
     ы
    0.62
     adenovirus
    0.62
     தமிழரசுக்
    0.60
     reactance
    0.59
     eukaryotic
    0.59
    依法
    0.58
     católica
    0.58
    サスカ
    0.57
    POSITIVE LOGITS
     chef
    1.42
     chefs
    1.42
     Chef
    1.39
     Chefs
    1.38
    Chef
    1.32
     Michelin
    1.30
    chefs
    1.22
    chef
    1.21
     terroir
    1.11
     foie
    1.08
    Activations Density 0.721%

    No Known Activations