© 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. 14297
    Prev
    Next
    INDEX
    Explanations

    torque transmission

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

    The neuron consistently detects the term “torque” (in all its morphological variants).

    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
    1
    -3.58
    a
    -3.23
    7
    -3.09
    s
    -3.02
    9
    -2.97
    ны
    -2.94
    es
    -2.89
     ‚
    -2.83
    p
    -2.73
     betreffenden
    -2.64
    POSITIVE LOGITS
    لفل
    2.84
    鸵
    2.70
    诘
    2.63
    逦
    2.63
     蕾
    2.55
    龊
    2.52
    骝
    2.47
    崃
    2.42
    逡
    2.28
    ᐡ
    2.25
    Activations Density 0.003%

    No Known Activations