© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62588
    Prev
    Next
    INDEX
    Explanations

    passenger reservation AC check

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    blos
    -0.80
    തി
    -0.77
    ба
    -0.73
    деля
    -0.72
    мм
    -0.71
     MacArthur
    -0.71
     lem
    -0.71
    Motor
    -0.71
    inSlope
    -0.70
    winkel
    -0.70
    POSITIVE LOGITS
     passenger
    1.02
     passengers
    0.93
     Passenger
    0.90
    passengers
    0.89
    Passenger
    0.89
    Passengers
    0.86
     itinerary
    0.86
     reservation
    0.85
     Passengers
    0.85
     confirmado
    0.79
    Activations Density 0.021%

    No Known Activations