© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6778
    Prev
    Next
    INDEX
    Explanations

    clutch engagement and shifting

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

    This neuron detects technical references to wet multi-plate clutch assemblies in automotive transmission contexts.

    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
    Prometheus
    -0.79
    prodi
    -0.73
     Binance
    -0.73
    瀵
    -0.73
    锡
    -0.71
    Parish
    -0.70
    錫
    -0.70
     Afghanistan
    -0.70
    richtungen
    -0.69
    dule
    -0.69
    POSITIVE LOGITS
     clutch
    1.67
     clutches
    1.54
    clutch
    1.26
     slipping
    1.11
     plates
    1.09
     friction
    1.04
    Clutch
    1.00
     Clutch
    0.99
     engagement
    0.97
     discs
    0.97
    Activations Density 0.046%

    No Known Activations