© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39950
    Prev
    Next
    INDEX
    Explanations

    HTML attributes after quotes

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

    The neuron flags occurrences of the token “stylesheet,” i.e. references to CSS stylesheet links in HTML.

    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
    Folge
    -1.47
     maniere
    -1.45
     maig
    -1.45
     Bahan
    -1.37
    읊
    -1.36
     現貨
    -1.34
     corriger
    -1.31
    Liefer
    -1.30
    Ainsi
    -1.28
    Zubereitung
    -1.27
    POSITIVE LOGITS
     and
    1.55
     for
    1.52
     "
    1.28
     referirse
    1.28
     here
    1.27
     like
    1.22
    了他的
    1.20
     L
    1.19
     betreff
    1.19
    atoday
    1.16
    Activations Density 0.006%

    No Known Activations