© 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. 112254
    Prev
    Next
    INDEX
    Explanations

    Bangkok and Norway

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

    The neuron activates on mentions of geographic place names (countries and major cities).

    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
    鸸
    -3.28
    祧
    -2.94
     啦
    -2.91
    ⚣
    -2.83
    ╹
    -2.72
    垸
    -2.72
    驁
    -2.67
    ?”
    -2.67
    
    -2.67
    pAd
    -2.59
    POSITIVE LOGITS
    0
    4.72
    –
    3.75
    c
    3.31
    »
    3.20
     {
    3.08
    5
    2.98
    t
    2.89
    IN
    2.89
    <i>
    2.89
    ↵↵
    2.88
    Activations Density 0.003%

    No Known Activations