© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103935
    Prev
    Next
    INDEX
    Explanations

    travel destinations and dates

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

    The neuron detects structured itinerary headings and date/day markers (e.g. “Day 1,” “Day 2,” schedule entries and other numeric travel-plan labels).

    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
     booking
    -0.91
    ссе
    -0.77
     bookings
    -0.77
    bigsqcup
    -0.75
    极限
    -0.73
    还有一个
    -0.71
     Booking
    -0.71
    瀨
    -0.71
    RawData
    -0.71
    booking
    -0.70
    POSITIVE LOGITS
     extensions
    1.13
    extension
    1.07
     extension
    1.00
     EXTENSION
    0.94
    extensions
    0.94
     Extensions
    0.92
    xtension
    0.92
    𝕮
    0.88
    Extensions
    0.86
     extending
    0.81
    Activations Density 0.015%

    No Known Activations