© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10871
    Prev
    Next
    INDEX
    Explanations

    wine and grapes

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

    words related to grapes, vineyards, and winemaking.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on mentions of grapes and grape‐derived things (wine, vineyards, vintners, grape fields, 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
    {
    -1.87
    “
    -1.84
    er
    -1.75
     a
    -1.70
    [
    -1.64
    @
    -1.63
    虚空
    -1.55
    ८
    -1.52
     ‘
    -1.51
    $.
    -1.50
    POSITIVE LOGITS
    鹮
    1.66
     実例
    1.63
     エントランス
    1.60
     aparat
    1.56
    ⓒ
    1.55
    튿
    1.55
    豨
    1.54
    獁
    1.54
     konkrete
    1.52
     abbildung
    1.50
    Activations Density 0.035%

    No Known Activations