© 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. 97984
    Prev
    Next
    INDEX
    Explanations

    riding vehicles

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

    The neuron selectively activates on verbs (and verb forms) that describe riding, mounting, dismounting, or otherwise traveling on vehicles.

    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
     hulls
    -0.74
     transacción
    -0.73
     να
    -0.72
     llevará
    -0.71
    ाली
    -0.70
     ഉ
    -0.69
     экспери
    -0.69
     драй
    -0.69
    bun
    -0.68
     jsonData
    -0.67
    POSITIVE LOGITS
     bike
    3.36
     bicycle
    3.20
     bicycles
    3.03
     bikes
    2.98
     motorcycle
    2.61
    bike
    2.44
     motorbike
    2.34
     motorcycles
    2.30
    Bike
    2.22
     велосипе
    2.22
    Activations Density 0.030%

    No Known Activations