© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73577
    Prev
    Next
    INDEX
    Explanations

    vehicle movement and parts

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

    The neuron fires on mentions of vehicles (cars, trucks, etc.) and associated automotive technical details (model names, numeric specs, violations).

    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
     Astrophysical
    -0.77
     biologists
    -0.74
    ulk
    -0.73
     Compiler
    -0.73
     DÍA
    -0.72
    راز
    -0.69
    كا
    -0.68
    washington
    -0.68
     stormwater
    -0.67
    Breath
    -0.67
    POSITIVE LOGITS
     driving
    0.86
     गा
    0.85
     wading
    0.83
    ohistochemical
    0.82
     license
    0.82
     Benz
    0.82
     chassis
    0.79
     configuration
    0.79
     Bär
    0.79
     configurations
    0.78
    Activations Density 0.013%

    No Known Activations