© 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. 102757
    Prev
    Next
    INDEX
    Explanations

    airline flights

    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
    脏
    -0.79
    izoen
    -0.76
    ^)／
    -0.75
    Faux
    -0.74
     Ports
    -0.73
    Tuition
    -0.73
    Fare
    -0.73
    yó
    -0.72
     Weltkrieg
    -0.71
    $.
    -0.71
    POSITIVE LOGITS
     flights
    3.75
     flight
    3.33
     Flights
    2.22
    flights
    2.05
    Flight
    2.03
     vuelos
    2.00
    航班
    1.98
    flight
    1.95
     Flight
    1.89
     vuelo
    1.88
    Activations Density 0.035%

    No Known Activations