© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116770
    Prev
    Next
    INDEX
    Explanations

    automotive windshield wipers

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

    The neuron fires on mentions of automotive hardware components—most strongly “windshield” and “wipers,” but also related vehicle parts like windows, headlights, sunroofs, lighting, and radio devices.

    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
    KeyDown
    -0.75
     Mehdi
    -0.74
    ↲
    -0.73
    Geschiedenis
    -0.73
    ₂
    -0.73
    蒴
    -0.71
     Apoptosis
    -0.71
    ︀
    -0.71
    Gateway
    -0.70
    flare
    -0.70
    POSITIVE LOGITS
     windshield
    2.91
     windscreen
    2.27
     wipers
    2.05
     wiper
    1.80
     Wind
    1.57
    wind
    1.47
    Wind
    1.32
     wind
    1.28
     defrost
    1.24
     Scheiben
    1.23
    Activations Density 0.017%

    No Known Activations