© 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. 100428
    Prev
    Next
    INDEX
    Explanations

    lubrication and lubricants

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

    This neuron detects occurrences of words containing the root “lubric” (e.g. lubricant, lubricating, lubrication, lubricity).

    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
    一首
    -3.05
    壜
    -2.42
     menyen
    -2.41
    〬
    -2.39
    嫫
    -2.34
    alakip
    -2.33
    ꪹ
    -2.30
    갛
    -2.20
     manoeu
    -2.19
    ⸂
    -2.19
    POSITIVE LOGITS
    -
    2.47
     of
    2.41
     wich
    2.36
     -
    2.34
    я
    2.30
     To
    2.28
    ၟ
    2.28
    ではでは
    2.23
    by
    2.22
     Perſ
    2.22
    Activations Density 0.003%

    No Known Activations