© 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. 118327
    Prev
    Next
    INDEX
    Explanations

    utm parameters in URLs

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

    The neuron is tuned to spotting UTM tracking parameters (like “utm_source=…”, “utm_medium=…”, etc.) in URLs.

    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
    羽毛
    -0.92
    MockBean
    -0.81
    ogna
    -0.81
     nedan
    -0.79
     slä
    -0.79
    icei
    -0.79
     edo
    -0.78
    wapV
    -0.77
    hancing
    -0.76
     įva
    -0.76
    POSITIVE LOGITS
     content
    1.24
     campaign
    1.18
    campaign
    0.94
     Campaign
    0.94
     term
    0.92
    content
    0.90
    Campaign
    0.90
     medium
    0.86
     source
    0.85
     CAMPAIGN
    0.84
    Activations Density 0.004%

    No Known Activations