© 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. 102568
    Prev
    Next
    INDEX
    Explanations

    common goals, India State, Boko Haram, Latin America, West Bank

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

    The neuron fires on geographic place names (countries, cities, regions) in the text.

    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
     menghubungi
    -0.93
     hitherto
    -0.93
    感恩
    -0.90
    Palestine
    -0.88
    Czym
    -0.82
     dainty
    -0.79
     progressive
    -0.79
     случи
    -0.79
    なかったので
    -0.79
     vehemently
    -0.78
    POSITIVE LOGITS
    ierte
    1.03
    ámetro
    0.99
    citement
    0.94
    İR
    0.93
    edded
    0.91
     innova
    0.91
    ició
    0.90
     robusta
    0.90
     bil
    0.87
     interloc
    0.87
    Activations Density 0.018%

    No Known Activations