© 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. 101666
    Prev
    Next
    INDEX
    Explanations

    Bootstrap UI framework

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

    references to the Bootstrap framework in code and documentation.

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

    The neuron flags mentions of front‐end UI frameworks or libraries (e.g. “Semantic UI,” “Bootstrap,” “Foundation”).

    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
    Because
    -1.55
    θεια
    -1.53
    。”
    -1.47
    What
    -1.38
    That
    -1.33
    Not
    -1.32
    /;
    -1.29
     萌
    -1.27
    6
    -1.25
    金
    -1.24
    POSITIVE LOGITS
     irmã
    1.34
    阖
    1.34
    罠
    1.33
     atrocious
    1.32
     aceite
    1.30
     exposiciones
    1.30
    malıdır
    1.27
    ただし
    1.27
     colegios
    1.27
     permitem
    1.26
    Activations Density 0.046%

    No Known Activations