© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93388
    Prev
    Next
    INDEX
    Explanations

    restaurants and hospitality

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

    This neuron detects terminology specific to the restaurant and hospitality industry (e.g., words like “hospitality,” “hotel,” “restaurant,” “food service,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     banyo
    -1.09
    padek
    -1.09
     будин
    -1.08
     diventa
    -1.06
     messaggi
    -1.05
     tvar
    -1.02
     farba
    -1.02
     diki
    -1.02
    ücks
    -1.02
    jandro
    -1.02
    POSITIVE LOGITS
     restaurant
    2.33
     hospitality
    1.52
     Restaurant
    1.50
     restaurants
    1.49
     hotel
    1.34
     nightclub
    1.29
     Hospitality
    1.27
     management
    1.21
     staff
    1.17
     beverage
    1.16
    Activations Density 0.072%

    No Known Activations