© 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. 22-GEMMASCOPE-RES-131K
    7. 129982
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out HTML/XML markup tokens (angle brackets, DOCTYPE, tag names, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    location or unicode

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     by
    -2.25
     having
    -1.59
     which
    -1.59
     all
    -1.51
     people
    -1.47
     for
    -1.44
     if
    -1.44
     almost
    -1.43
     any
    -1.41
     have
    -1.41
    POSITIVE LOGITS
     trám
    1.45
    為に
    1.45
    indicate
    1.43
     betreffende
    1.23
     ainfi
    1.20
    ७
    1.20
     momentous
    1.19
     Ô
    1.18
     ☺️
    1.17
     GOtt
    1.17
    Activations Density 0.141%

    No Known Activations