© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44353
    Prev
    Next
    INDEX
    Explanations

    place names and surnames

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

    The neuron detects proper‐noun tokens—that is, capitalized names of people, places, or other named entities.

    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
    0
    -3.41
    a
    -3.08
    ll
    -2.88
    ↵
    -2.84
    z
    -2.77
    ed
    -2.73
    an
    -2.67
    -2.67
     capa
    -2.64
    acterísticas
    -2.64
    POSITIVE LOGITS
     erhielten
    2.47
    ﺢ
    2.41
    "
    2.34
    阗
    2.34
     スタン
    2.31
    日閲覧
    2.30
    镭
    2.28
    薔薇
    2.28
    אין
    2.25
    vantaged
    2.23
    Activations Density 0.036%

    No Known Activations