© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39249
    Prev
    Next
    INDEX
    Explanations

    utm_ tracking parameters

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

    The neuron detects URL query parameters, especially UTM tracking tokens (e.g. “utm_…” and related numeric values and separators).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    всем
    -1.52
     vė
    -1.47
    !!!!!!
    -1.44
    meability
    -1.43
     Ál
    -1.43
     Of
    -1.41
    胤
    -1.37
    局面
    -1.36
     įva
    -1.36
     vienas
    -1.35
    POSITIVE LOGITS
     allmäh
    1.50
    leggio
    1.48
    說道
    1.45
    ip
    1.41
    _
    1.38
    嘮
    1.34
    やってきた
    1.33
    oids
    1.32
    o
    1.31
    餮
    1.30
    Activations Density 0.001%

    No Known Activations