© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29041
    Prev
    Next
    INDEX
    Explanations

    lists of countries and places

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

    The neuron strongly activates on country and other geographic location names.

    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
    鹩
    -1.92
     cũng
    -1.74
     også
    -1.69
     escalier
    -1.62
     énon
    -1.59
     ส์
    -1.59
     sépar
    -1.55
     גם
    -1.52
    ſelf
    -1.49
     activado
    -1.49
    POSITIVE LOGITS
    in
    2.52
     to
    1.87
     of
    1.73
     where
    1.72
     other
    1.63
     various
    1.56
     with
    1.55
     some
    1.52
    by
    1.51
    ."
    1.45
    Activations Density 0.045%

    No Known Activations