© 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. 38561
    Prev
    Next
    INDEX
    Explanations

    table at, reservations:

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

    The neuron is triggered by multiword verb constructions (auxiliary or modal plus main verb), e.g. “waiting to get” or “were told by.”

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

    phrases describing limited availability or seating that requires reservations or early arrival.

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

    mentions of restaurants, bars, or events with logistics of getting in—waiting for a table, reservations, seating, or admission policies.

    oai_token-act-pair · gpt-5Triggered 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
     lancia
    -0.89
    fps
    -0.87
     Bolsonaro
    -0.86
     indiví
    -0.79
     خریدار
    -0.79
     solida
    -0.77
     Malk
    -0.76
     schia
    -0.75
     incontri
    -0.75
    dateien
    -0.75
    POSITIVE LOGITS
     seating
    2.28
     hostess
    1.91
     seated
    1.91
     seat
    1.64
     seats
    1.61
    seated
    1.54
     Seating
    1.48
     table
    1.44
     reservation
    1.43
     reservations
    1.35
    Activations Density 0.006%

    No Known Activations