© 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. 92333
    Prev
    Next
    INDEX
    Explanations

    rides, bike, games, events

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

    This neuron fires on occurrences of the word “ride” (and its variants like “riding”) and related forms (e.g. “bike”), effectively detecting mentions of riding.

    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
    f
    -1.14
    k
    -1.13
    2
    -1.05
    \
    -1.04
    c
    -1.04
    v
    -1.04
    as
    -1.03
    ad
    -1.03
    n
    -1.02
     {
    -0.99
    POSITIVE LOGITS
     Ride
    1.38
     Rides
    1.16
     ride
    1.11
    Ride
    1.09
     RIDE
    1.09
    ride
    1.08
    Rebs
    1.08
     ofici
    1.05
    Ruj
    1.02
     první
    1.02
    Activations Density 0.008%

    No Known Activations