© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    airline and airport related terms

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

    booking flights and airports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ꮁ
    0.43
     संज्ञा
    0.42
     NumericVector
    0.40
    ネス
    0.39
    不动
    0.39
     Heterocycl
    0.39
     Kün
    0.39
     হুগ
    0.39
     町
    0.39
     Wasserstein
    0.39
    POSITIVE LOGITS
     airline
    2.72
     airport
    2.66
     airlines
    2.58
     airports
    2.52
    airport
    2.50
     flights
    2.48
     flight
    2.45
    机场
    2.44
     항공
    2.44
     Airline
    2.44
    Activations Density 0.459%

    No Known Activations