© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93124
    Prev
    Next
    INDEX
    Explanations

    coaching and assistant roles

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

    This neuron detects mentions of professional sports coaching or managerial roles (e.g., words like “assistant,” “coach,” “manager,” and “career”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     more
    -0.93
     चीज़
    -0.92
     corretamente
    -0.92
     televisor
    -0.91
     auriculares
    -0.90
     莉
    -0.88
    クタ
    -0.88
     this
    -0.88
    ئین
    -0.88
     الشهر
    -0.86
    POSITIVE LOGITS
     coaching
    1.48
     assistant
    1.39
     teaching
    1.37
    teaching
    1.26
     assist
    1.22
    coaching
    1.21
     membantu
    1.20
     coach
    1.16
     assistants
    1.09
     conseiller
    1.09
    Activations Density 0.028%

    No Known Activations