© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58377
    Prev
    Next
    INDEX
    Explanations

    http://www.w3.org/ namespaces

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

    The neuron is triggered by XML namespace declarations—specifically the xmlns="http://www.w3.org/…" URL tokens.

    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
     lumine
    -0.94
    ạch
    -0.89
     maig
    -0.82
    teiro
    -0.81
     Marten
    -0.80
     pneus
    -0.80
     médias
    -0.79
    sieger
    -0.79
    蛋糕
    -0.78
    APER
    -0.78
    POSITIVE LOGITS
     http
    1.38
    http
    1.34
     https
    1.30
    https
    1.12
     URL
    0.84
    咳咳
    0.81
    urn
    0.81
    mittedly
    0.79
     Unsere
    0.79
     www
    0.78
    Activations Density 0.009%

    No Known Activations