© 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. 34-GEMMASCOPE-RES-131K
    7. 119323
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and component properties

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

    The neuron fires on the opening angle bracket of HTML/JSX tags.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    けれど
    -0.93
    Herkunft
    -0.91
     southward
    -0.89
     همچ
    -0.88
    ukunfts
    -0.85
    Какой
    -0.84
    zmm
    -0.84
     "'");
    -0.83
     サンプル
    -0.83
     toothed
    -0.83
    POSITIVE LOGITS
    {...
    1.09
     />
    1.02
     className
    1.00
     {...
    0.92
     style
    0.88
     on
    0.86
    className
    0.84
    ⬇️
    0.84
     height
    0.84
    />
    0.81
    Activations Density 0.011%

    No Known Activations