© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19926
    Prev
    Next
    INDEX
    Explanations

    physical exercise and training

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

    The neuron strongly activates on the word “exercise” (and its close morphological variants), signaling mentions of exercise or physical training.

    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
    '
    -3.14
    /
    -2.33
    \'
    -2.03
    就直接
    -2.02
    目前的
    -1.98
     consegu
    -1.96
     poupée
    -1.92
    厳選
    -1.92
    as
    -1.90
    就去
    -1.89
    POSITIVE LOGITS
    ↵↵
    2.98
     Когда
    2.33
    ?”
    2.25
    มัน
    2.19
     hilfreich
    2.16
    !”
    2.16
    㩒
    2.13
    Достоинства
    2.11
    你
    2.05
     炒め
    2.02
    Activations Density 0.019%

    No Known Activations