© 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. 63984
    Prev
    Next
    INDEX
    Explanations

    InfoWindow, marker, map

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

    This neuron fires on code or discussion of map‐marker APIs—e.g. references to Mapbox, Google Maps/Leaflet markers, infoWindows, and related mapping functions.

    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
    Diagram
    -0.74
     gemeint
    -0.69
    Unione
    -0.67
    哪儿
    -0.66
    هد
    -0.66
     pizzas
    -0.66
     навер
    -0.66
    =-\
    -0.65
     barrier
    -0.65
     العالم
    -0.65
    POSITIVE LOGITS
    InfoWindow
    1.39
     info
    1.27
     getInfo
    1.20
     Info
    1.17
     INFO
    1.17
    info
    1.15
    getInfo
    1.06
     popup
    1.06
    INFO
    0.99
    Marker
    0.98
    Activations Density 0.027%

    No Known Activations