© 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. 23887
    Prev
    Next
    INDEX
    Explanations

    people and places names

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

    This neuron detects capitalized proper names (people and place names) 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_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
    栳
    -2.67
    佧
    -2.67
    י
    -2.63
    嫱
    -2.58
    떳
    -2.52
    籀
    -2.50
    
    -2.42
    遢
    -2.33
    föra
    -2.33
    indelijk
    -2.31
    POSITIVE LOGITS
    ية
    2.78
    as
    2.45
    </h3>
    2.38
    ’
    2.30
    “
    2.23
     your
    2.19
    o
    2.19
     む
    2.09
    "
    2.09
    .
    2.02
    Activations Density 0.003%

    No Known Activations