© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70422
    Prev
    Next
    INDEX
    Explanations

    bour names and places

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

    This neuron detects occurrences of the letter sequence “bour” (as found in names like Bourdon, Bourges, Bourne, 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
    if
    -3.20
     unſ
    -3.03
    薆
    -2.56
    offers
    -2.38
    ޏ
    -2.30
    とても
    -2.27
     Reſ
    -2.25
     greateſt
    -2.23
    会
    -2.23
    this
    -2.22
    POSITIVE LOGITS
     It
    2.77
    戽
    2.53
     Alongside
    2.53
     ostensibly
    2.52
     Somebody
    2.47
     Additionally
    2.44
     Another
    2.41
     vehemently
    2.39
     hastily
    2.39
     foremost
    2.39
    Activations Density 0.002%

    No Known Activations