© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47128
    Prev
    Next
    INDEX
    Explanations

    chairing

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

    The neuron activates on mentions of organizing or running professional events—e.g. chairing conferences, introducing keynotes, or moderating panels.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    IDTH
    -0.83
    urfs
    -0.81
     Checkpoint
    -0.78
    gató
    -0.77
     sınır
    -0.77
     checkpoints
    -0.71
    オシャレ
    -0.70
    iann
    -0.69
     magnifiques
    -0.69
     güç
    -0.69
    POSITIVE LOGITS
     chaired
    5.03
     cha
    4.88
     Cha
    3.77
    cha
    3.55
    Cha
    3.53
     chair
    3.48
     Chair
    2.89
     chairs
    2.83
    chair
    2.77
    Chair
    2.73
    Activations Density 0.065%

    No Known Activations