© 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. 34-GEMMASCOPE-RES-131K
    4. 103027
    Prev
    Next
    INDEX
    Explanations

    set up or set to

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

    The neuron reliably fires on occurrences of the word “set.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     thông
    -0.79
    hita
    -0.79
    Figures
    -0.74
    活力
    -0.73
    颜色
    -0.73
    それが
    -0.71
     matéria
    -0.71
    ेड
    -0.71
    one
    -0.71
    hadores
    -0.70
    POSITIVE LOGITS
     up
    1.13
     against
    0.96
     apart
    0.90
    ``.
    0.88
    meist
    0.88
    pieces
    0.85
     to
    0.84
     pieces
    0.83
    定価
    0.81
    piece
    0.80
    Activations Density 0.024%

    No Known Activations