© 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. 10-GEMMASCOPE-RES-131K
    7. 99867
    Prev
    Next
    INDEX
    Explanations

    international airports

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

    This neuron identifies mentions of airports—especially the word “airport,” “International,” and accompanying airport codes or 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_10/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
     Vea
    -1.27
    ֝
    -1.24
    </i>
    -1.23
    ㆆ
    -1.20
     against
    -1.19
    .”
    -1.18
    mathrm
    -1.18
     verwende
    -1.17
    ARCHITECTURE
    -1.16
    </h3>
    -1.15
    POSITIVE LOGITS
     to
    1.48
     only
    1.31
     Airport
    1.30
     airports
    1.20
     handel
    1.20
    Кита
    1.18
    ization
    1.17
    phòng
    1.15
     airport
    1.13
    穑
    1.13
    Activations Density 0.033%

    No Known Activations