© 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. 57424
    Prev
    Next
    INDEX
    Explanations

    master followed by noun

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

    The neuron activates on the word “master” (especially when it appears in compound technical terms like master key, master clock, or master cylinder).

    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
     virksom
    -1.87
    bezpe
    -1.75
    🫃
    -1.47
     medarbe
    -1.45
    ologies
    -1.40
    hows
    -1.35
     nhat
    -1.34
     trám
    -1.32
    cares
    -1.32
     AMERICA
    -1.32
    POSITIVE LOGITS
     master
    2.06
    Another
    1.69
    Although
    1.57
    During
    1.52
     will
    1.51
     there
    1.42
    Following
    1.41
    master
    1.38
     Master
    1.38
    Master
    1.37
    Activations Density 0.056%

    No Known Activations