© 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. 10-GEMMASCOPE-RES-131K
    4. 110887
    Prev
    Next
    INDEX
    Explanations

    flex-wrap, flex-direction, column

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

    the word "wrap" in CSS and UI layout contexts (flex-wrap, wrap_content, text wrapping).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on occurrences of the keyword “wrap” (e.g. flex-wrap, wrap_content).

    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
     pôr
    -1.34
    bjs
    -1.31
    絰
    -1.29
    1
    -1.27
    mpagne
    -1.26
    enablog
    -1.21
    reasonably
    -1.20
    -\\
    -1.20
     posed
    -1.18
     чёр
    -1.18
    POSITIVE LOGITS
     There
    1.45
    StoryboardSegue
    1.45
     Unlike
    1.37
    王妃
    1.33
     Making
    1.33
     This
    1.33
     Interestingly
    1.32
    勅
    1.32
     Trying
    1.31
    êtes
    1.29
    Activations Density 0.006%

    No Known Activations