© 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. 77846
    Prev
    Next
    INDEX
    Explanations

    bearings and balls

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

    The neuron fires on technical mechanical component terms—especially “bearing” (and related shaft, input, gear, etc.)—as typically found in patent‐style descriptions.

    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
    ilig
    -0.74
     klaar
    -0.73
    кора
    -0.73
    klen
    -0.73
    ฿
    -0.72
    Formik
    -0.71
     Ú
    -0.71
    inate
    -0.71
    ograft
    -0.70
    thereal
    -0.69
    POSITIVE LOGITS
     bearings
    2.55
     bearing
    2.53
    Bearing
    2.13
     Bearing
    2.09
    bearing
    2.06
     Bearings
    2.05
     balls
    1.52
    bear
    1.44
    Balls
    1.39
    Bear
    1.29
    Activations Density 0.037%

    No Known Activations