© 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. 60104
    Prev
    Next
    INDEX
    Explanations

    airport and airfield operations

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

    The neuron strongly activates on mentions of airports (e.g. the word “Airport” and airport names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     carriages
    -0.96
     Prudential
    -0.75
     Kais
    -0.75
     frigate
    -0.74
    运
    -0.73
    故障
    -0.73
    BASS
    -0.73
     MMC
    -0.72
     QName
    -0.72
    esModule
    -0.72
    POSITIVE LOGITS
     airport
    1.33
    Airport
    1.20
     Airport
    1.19
     airfield
    1.10
    airport
    1.05
    机场
    1.00
     FAA
    0.99
     Flughafen
    0.99
     airports
    0.96
     reliever
    0.93
    Activations Density 0.032%

    No Known Activations