© 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. 34-GEMMASCOPE-RES-131K
    7. 25835
    Prev
    Next
    INDEX
    Explanations

    food service and events

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

    The neuron fires on mentions of food and drink offerings—menu and catering items like hors d’oeuvres, bar service, and dishes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     pancakes
    -0.86
    жий
    -0.85
     fries
    -0.81
     Elmer
    -0.76
     possessor
    -0.76
     WEEKLY
    -0.76
     médicament
    -0.75
     weekdays
    -0.75
    pherals
    -0.73
    ionista
    -0.73
    POSITIVE LOGITS
     stations
    1.58
     served
    1.41
     buffet
    1.31
     choice
    1.26
     passed
    1.25
     Stations
    1.20
     station
    1.17
    plated
    1.17
     butler
    1.16
    stations
    1.12
    Activations Density 0.011%

    No Known Activations