© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70613
    Prev
    Next
    INDEX
    Explanations

    Master followed by titles or roles

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

    The neuron is triggered by the word “Master” when it appears as a standalone title (e.g. “Master Tejas,” “Master Yang,” 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
    橛
    -2.64
    韪
    -2.61
    閙
    -2.59
    
    -2.58
    嫘
    -2.50
    屺
    -2.50
    壆
    -2.48
    せよ
    -2.42
    螃
    -2.41
    requipa
    -2.39
    POSITIVE LOGITS
    What
    4.59
    With
    4.44
    From
    4.06
    Although
    3.95
    Now
    3.94
    While
    3.88
    Since
    3.83
    After
    3.83
    When
    3.70
    How
    3.67
    Activations Density 0.003%

    No Known Activations