© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85632
    Prev
    Next
    INDEX
    Explanations

    maps, location, markers, coordinates

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

    The neuron fires on technical programming identifiers—class, API, and function names (e.g. Mapbox, InfoWindow, LatLng, LocationService, DesiredAccuracy, MFMailComposeViewController).

    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
    ↵↵
    -1.73
     bestimmen
    -1.45
     =
    -1.44
    in
    -1.43
    es
    -1.41
    дии
    -1.41
    helia
    -1.39
    ")
    -1.38
     eğer
    -1.38
     -
    -1.37
    POSITIVE LOGITS
     kock
    1.40
     kalend
    1.34
     laim
    1.32
     hırka
    1.30
    coglie
    1.29
     videa
    1.28
     ieg
    1.28
     ered
    1.27
    Formik
    1.24
     projets
    1.23
    Activations Density 0.010%

    No Known Activations