© 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. 103599
    Prev
    Next
    INDEX
    Explanations

    managing travel booking data

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

    The neuron fires on mentions of concrete domain‐specific entity names or data model terms (e.g. class names like Trip or Stop and real‐world categories like travel, databases, hotels).

    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
    上角
    -0.96
     publicKey
    -0.86
     relocated
    -0.86
    viale
    -0.82
     магазине
    -0.82
    ాన
    -0.81
     imports
    -0.78
    وارد
    -0.76
     importers
    -0.75
     teolog
    -0.75
    POSITIVE LOGITS
     booking
    2.17
     travel
    1.82
     hotel
    1.82
     tourist
    1.77
     hotels
    1.76
     Booking
    1.67
     tourism
    1.67
     itinerary
    1.66
    Booking
    1.66
     trip
    1.65
    Activations Density 0.012%

    No Known Activations