© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69664
    Prev
    Next
    INDEX
    Explanations

    finesse and sophistication

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

    The neuron strongly responds to French‐derived flair/style nouns or names (e.g. “finesse,” “fineness,” “panache,” “éclat,” “Fortessa”)—in other words, words that connote elegance, flair, or brilliance.

    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
     the
    -2.64
    猻
    -2.52
    鐃
    -2.34
    蜴
    -2.31
    ↑
    -2.30
     imprensa
    -2.14
     in
    -2.13
     versão
    -2.08
    虯
    -2.08
     dictates
    -2.02
    POSITIVE LOGITS
    A
    2.53
     finesse
    2.42
    .
    2.41
    F
    2.28
    渕
    2.25
    ทั้ง
    2.22
    This
    2.16
    多くの
    2.06
    Also
    2.02
     الذي
    2.00
    Activations Density 0.003%

    No Known Activations