© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29974
    Prev
    Next
    INDEX
    Explanations

    GPS and GNSS navigation

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

    The neuron strongly activates on mentions of satellite‐based positioning systems, especially on their acronyms like GNSS or GPS.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    SOA
    -0.77
    עוד
    -0.73
     Eldridge
    -0.73
     grinding
    -0.73
    Kevin
    -0.73
     Grinding
    -0.71
     antigas
    -0.70
     الرسمي
    -0.68
    sean
    -0.67
     SOA
    -0.67
    POSITIVE LOGITS
     GPS
    5.66
    GPS
    4.78
     gps
    4.28
    gps
    4.06
    Gps
    3.31
     GN
    2.48
     GPs
    2.00
    GN
    1.79
     Garmin
    1.75
     satellite
    1.72
    Activations Density 0.080%

    No Known Activations