© 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. 45428
    Prev
    Next
    INDEX
    Explanations

    East African countries and geography

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

    The neuron activates on mentions of African place names or geographic locations (countries, regions, towns, etc.).

    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
    廿
    -0.69
    三浦
    -0.68
    THISDAY
    -0.65
    isticated
    -0.65
    Neat
    -0.65
    emlrt
    -0.64
     Masse
    -0.63
    msgSender
    -0.63
     modelAndView
    -0.63
    <?
    -0.63
    POSITIVE LOGITS
    grun
    0.90
     Ethiopia
    0.86
    Redux
    0.83
     Jupyter
    0.81
     আম
    0.80
     numerosi
    0.80
    🇰
    0.79
     Djibouti
    0.78
     hecta
    0.77
     predominantly
    0.77
    Activations Density 0.007%

    No Known Activations