© 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. 63112
    Prev
    Next
    INDEX
    Explanations

    clutch and related automotive parts

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

    The neuron strongly activates on highly technical terms related to hydraulic clutch actuation systems.

    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
     conmemor
    -0.81
    Crist
    -0.79
     расши
    -0.78
     encaje
    -0.75
     Христо
    -0.74
     koş
    -0.71
     Latvian
    -0.71
    forecast
    -0.71
    omorphic
    -0.71
     toprak
    -0.70
    POSITIVE LOGITS
     clutch
    2.47
     Clutch
    1.87
    Clutch
    1.79
    clutch
    1.78
     flywheel
    1.77
     clutches
    1.41
     embrague
    1.18
     clutched
    1.18
     Fly
    1.17
    fly
    1.16
    Activations Density 0.019%

    No Known Activations