© 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. 130243
    Prev
    Next
    INDEX
    Explanations

    specialist in a field

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

    The neuron fires on mentions of “specialist” (and its variants like “specialists”), i.e. labels identifying a specialized professional role.

    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
     básicamente
    -1.69
    で一番
    -1.62
     and
    -1.58
     parfü
    -1.58
     any
    -1.52
     algunos
    -1.51
     españolas
    -1.50
     otras
    -1.49
    だったら
    -1.46
     galería
    -1.45
    POSITIVE LOGITS
     who
    2.08
     to
    2.02
    饪
    1.87
     做
    1.82
    廔
    1.77
    蛱
    1.71
     در
    1.62
     这个
    1.61
     این
    1.59
     показатели
    1.55
    Activations Density 0.020%

    No Known Activations