© 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. 34-GEMMASCOPE-RES-131K
    7. 63318
    Prev
    Next
    INDEX
    Explanations

    sports coaches and managers

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

    The neuron detects mentions of sports team leadership roles—especially words like “coach,” “manager,” or similar titles.

    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
     excel
    -0.75
    ῴ
    -0.74
     Ivan
    -0.73
     Administrator
    -0.72
    าน
    -0.71
    marginRight
    -0.70
    !”
    -0.69
    涿
    -0.69
    login
    -0.69
    reuung
    -0.69
    POSITIVE LOGITS
     coaching
    1.10
    Coaching
    1.07
    coaching
    1.02
     Coaching
    1.00
     fired
    0.86
     assistants
    0.80
    Assistant
    0.79
     behind
    0.78
     Carlyle
    0.78
    Associate
    0.76
    Activations Density 0.024%

    No Known Activations