© 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. 103615
    Prev
    Next
    INDEX
    Explanations

    hotel stay

    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
    Not in Any Lists

    No Comments

    Negative Logits
    arschu
    -1.19
     today
    -1.09
    ษัท
    -1.09
    ଷ
    -1.04
     producing
    -1.02
     Inseln
    -0.95
    xfc
    -0.94
     produce
    -0.94
    ﷺ
    -0.93
    vdash
    -0.93
    POSITIVE LOGITS
     hotel
    1.71
     booking
    1.67
     accommodation
    1.53
     stay
    1.45
     Booking
    1.40
    Booking
    1.38
     rooms
    1.38
     hotels
    1.28
     booked
    1.27
     TripAdvisor
    1.20
    Activations Density 0.025%

    No Known Activations