© 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. 64023
    Prev
    Next
    INDEX
    Explanations

    coach, coaching, and related roles

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

    The neuron activates on occurrences of the word “coach” (and its variants) when it names or refers to a coaching role.

    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
    arlı
    -0.97
     enrolling
    -0.94
     incredibly
    -0.91
     adjoining
    -0.89
     delightful
    -0.89
     mittleren
    -0.88
     acutely
    -0.88
    REFERRED
    -0.87
     contemplating
    -0.86
    えられる
    -0.86
    POSITIVE LOGITS
    Coaching
    1.05
    ৣ
    1.05
    ング
    1.05
    erey
    1.04
     coaching
    1.03
    coaching
    1.02
     Coach
    0.97
    meneu
    0.97
    −/−
    0.96
    rators
    0.96
    Activations Density 0.009%

    No Known Activations