© 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. 64981
    Prev
    Next
    INDEX
    Explanations

    traffic congestion and roads

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

    The neuron strongly activates on terms related to road traffic and congestion.

    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
    orthand
    -0.90
     Flugzeug
    -0.88
    èrement
    -0.84
    特急
    -0.80
     derniers
    -0.79
    omes
    -0.78
     Uttarakhand
    -0.77
     wobble
    -0.77
    olito
    -0.77
    %">
    -0.77
    POSITIVE LOGITS
     traffic
    3.33
     congestion
    2.77
    traffic
    2.53
    Traffic
    2.25
     Traffic
    2.20
     congested
    2.08
     TRAFFIC
    1.82
     conges
    1.63
     roads
    1.61
     tráfico
    1.61
    Activations Density 0.039%

    No Known Activations