© 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. 10-GEMMASCOPE-RES-131K
    7. 19304
    Prev
    Next
    INDEX
    Explanations

    names of people and cities

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

    The neuron lights up on proper‐noun tokens, i.e. names of people, bands, companies, products, websites, 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_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
     они
    -2.22
    ⬮
    -2.13
    罴
    -1.95
    𐑂
    -1.95
     hän
    -1.88
    $
    -1.77
    ⢅
    -1.71
     Diese
    -1.66
    ۲
    -1.65
     diese
    -1.63
    POSITIVE LOGITS
     État
    1.89
    ynı
    1.86
    隄
    1.84
    椟
    1.77
    ”、“
    1.70
    籏
    1.70
    垰
    1.67
    窺
    1.65
     Ciclo
    1.63
     fará
    1.63
    Activations Density 0.002%

    No Known Activations