© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64174
    Prev
    Next
    INDEX
    Explanations

    TripAdvisor and travel reviews

    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
     metus
    -0.94
     highschool
    -0.81
    asgi
    -0.73
     client
    -0.73
     thirds
    -0.72
     магазин
    -0.72
    ٻ
    -0.72
    ector
    -0.71
    一流
    -0.71
    ecks
    -0.71
    POSITIVE LOGITS
     TripAdvisor
    1.92
     Trip
    1.60
    Trip
    1.49
     reviews
    1.46
     reviewers
    1.22
    reviews
    1.16
     TRIP
    1.14
     Travellers
    1.08
    TRIP
    1.04
     ratings
    1.03
    Activations Density 0.009%

    No Known Activations