© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71681
    Prev
    Next
    INDEX
    Explanations

    board members and directors

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

    The neuron activates on mentions of “board” or “Board” in contexts like “board of directors” or “board member.”

    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
    vantaged
    -2.02
     ότι
    -1.77
     enthalten
    -1.73
    ミン
    -1.70
    縢
    -1.68
     что
    -1.61
    Basically
    -1.60
    Theres
    -1.60
    可不是
    -1.57
    倏
    -1.57
    POSITIVE LOGITS
     possa
    2.00
     of
    1.92
     segni
    1.88
    ❓
    1.82
    I
    1.81
    勠
    1.79
    🌼
    1.74
    💓
    1.70
    ☘
    1.70
    🌷
    1.68
    Activations Density 0.015%

    No Known Activations