© 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. 86996
    Prev
    Next
    INDEX
    Explanations

    bus service

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

    The neuron flags mentions of public transit modes and infrastructure (e.g. “transit,” “bus,” “metro,” “railway,” 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
    distrito
    -0.73
     SNCF
    -0.72
    ಾಗಿ
    -0.70
    remp
    -0.70
    DISTRICT
    -0.69
     consiglio
    -0.69
    cussion
    -0.68
     scom
    -0.68
    SPEAKER
    -0.68
     mangiare
    -0.68
    POSITIVE LOGITS
     Bus
    1.55
     bus
    1.47
    Bus
    1.36
    bus
    1.14
     BUS
    1.13
     rapid
    1.09
     Rapid
    1.06
     buses
    1.05
     corridor
    1.02
    BR
    0.98
    Activations Density 0.016%

    No Known Activations