© 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. 19066
    Prev
    Next
    INDEX
    Explanations

    people

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

    The neuron responds to the word “people” (and its variants), marking mentions of people or population.

    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
    gebras
    -1.88
    щита
    -1.85
     în
    -1.82
    鲥
    -1.80
    Ꮠ
    -1.79
     sont
    -1.77
    idemia
    -1.76
    γω
    -1.76
     امریک
    -1.72
     моя
    -1.71
    POSITIVE LOGITS
    .
    2.31
     The
    2.31
    '
    1.95
     to
    1.91
    struzioni
    1.49
    de
    1.48
     They
    1.47
     gabri
    1.47
     Following
    1.43
     generó
    1.43
    Activations Density 0.005%

    No Known Activations