© 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. 25739
    Prev
    Next
    INDEX
    Explanations

    ride, riding, rides

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

    This neuron detects occurrences of the root “rid” (as in ride, rider, riding, ridership, piggy-backing, etc.).

    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
    report
    -0.79
     Running
    -0.77
    radial
    -0.75
     Returning
    -0.75
     Retention
    -0.73
    retention
    -0.73
    cazione
    -0.72
    returning
    -0.70
     Rectangular
    -0.70
    reach
    -0.68
    POSITIVE LOGITS
     ride
    5.22
     riding
    4.31
     rides
    4.28
    Ride
    3.45
    ride
    3.34
     Ride
    3.28
     rode
    2.94
     RIDE
    2.92
    Riding
    2.86
     riders
    2.80
    Activations Density 0.059%

    No Known Activations