© 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. 22-GEMMASCOPE-RES-131K
    7. 70497
    Prev
    Next
    INDEX
    Explanations

    XML/HTML dimension tags or attributes

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

    The neuron specifically lights up for the “width” attribute name in XML/HTML‐style 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_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
     when
    -1.92
     or
    -1.77
     for
    -1.75
    when
    -1.68
    When
    -1.67
     after
    -1.65
    After
    -1.49
    While
    -1.45
     When
    -1.44
     During
    -1.38
    POSITIVE LOGITS
     fabulous
    1.37
     ジップ
    1.27
     réparer
    1.27
     quadrado
    1.25
     cliquer
    1.24
     hinh
    1.23
     défauts
    1.23
     cuadrado
    1.23
     unbelievably
    1.21
     importación
    1.21
    Activations Density 0.000%

    No Known Activations