© 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. 22-GEMMASCOPE-RES-131K
    7. 104709
    Prev
    Next
    INDEX
    Explanations

    cities, countries, and home

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

    The neuron strongly activates on geographic place names (cities, countries, 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_22/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
     täh
    -1.16
     femininos
    -0.91
    华为
    -0.89
    navBar
    -0.87
    ฉัน
    -0.87
     dianteiro
    -0.86
     hôte
    -0.86
     libération
    -0.85
    鸚
    -0.85
     dernière
    -0.84
    POSITIVE LOGITS
     where
    1.02
     home
    0.94
     olması
    0.88
    lně
    0.87
     usual
    0.87
     menilai
    0.86
    通常
    0.85
    amenti
    0.82
    where
    0.80
     runs
    0.79
    Activations Density 0.023%

    No Known Activations