© 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. 10-GEMMASCOPE-RES-131K
    7. 65585
    Prev
    Next
    INDEX
    Explanations

    HTML option tags

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

    The neuron fires on HTML form select controls and their option elements, i.e. it looks for select/option markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    probieren
    -1.43
     pubblicazione
    -1.40
    是一个
    -1.40
     Reſ
    -1.37
     Inſ
    -1.37
    鎬
    -1.36
     decisione
    -1.36
    GIN
    -1.34
     Diſ
    -1.32
    LayoutConstraint
    -1.31
    POSITIVE LOGITS
     are
    1.40
     nyingi
    1.32
    é
    1.29
     mutta
    1.28
    됨
    1.27
     only
    1.25
    复古
    1.23
     one
    1.19
     Many
    1.16
    简约
    1.16
    Activations Density 0.033%

    No Known Activations