© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8145
    Prev
    Next
    INDEX
    Explanations

    taxi and ride-sharing services

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

    The neuron fires on mentions of limousine services—i.e. occurrences of “limo,” “limousine,” and related transport-service terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REACTOR
    0.64
     जिम
    0.61
    unst
    0.57
     gym
    0.56
     REACTOR
    0.56
    🧗
    0.54
     Gym
    0.53
    hashTree
    0.53
     лест
    0.53
    বিক
    0.52
    POSITIVE LOGITS
     taxi
    2.11
    Taxi
    2.02
     Taxi
    1.99
     taxis
    1.99
    taxi
    1.84
     Uber
    1.65
     chauffeur
    1.61
    Uber
    1.60
    🚕
    1.52
     cabs
    1.47
    Activations Density 0.280%

    No Known Activations