© 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. 10-GEMMASCOPE-RES-131K
    7. 15092
    Prev
    Next
    INDEX
    Explanations

    coach, coaching

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

    The neuron fires on mentions of “coach” and its inflected forms (coaching, coached, coaches, 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_10/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
    </h3>
    -1.98
    を中心
    -1.94
     Featuring
    -1.89
    1
    -1.88
     einzigartigen
    -1.83
    遯
    -1.80
     So
    -1.78
     Including
    -1.77
    mô
    -1.77
    Zubereitung
    -1.76
    POSITIVE LOGITS
    x
    2.14
     CascadeType
    2.14
    дәбият
    2.13
    }$.
    2.13
    zers
    2.09
    年
    2.06
    ir
    2.05
    ではでは
    2.03
     尔
    2.02
    怜
    1.95
    Activations Density 0.010%

    No Known Activations