© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73513
    Prev
    Next
    INDEX
    Explanations

    coaches and coaching

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

    The neuron is strongly activated by named entities and salient numeric information (people’s names, teams, dates, ages, stats, 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_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
     tež
    -0.89
     vocalist
    -0.89
    TabStop
    -0.89
    juje
    -0.88
    텐츠
    -0.88
     classmate
    -0.85
    ongiorno
    -0.83
    ಅ
    -0.83
     acrob
    -0.82
     teammate
    -0.81
    POSITIVE LOGITS
     coaching
    2.72
     coaches
    2.30
     coach
    2.20
    coaching
    2.16
     Coaching
    2.00
    Coaching
    1.98
     COACH
    1.84
     Coaches
    1.80
     Coach
    1.78
    COACH
    1.71
    Activations Density 0.063%

    No Known Activations