© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33722
    Prev
    Next
    INDEX
    Explanations

    html tag attributes and values

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

    The neuron is specialized to pick out CSS‐ and HTML layout/styling tokens (e.g. class names, Bootstrap grid classes, style values, color names, percentage or pixel dimensions).

    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
    ほら
    -1.41
     zwięks
    -1.34
     daarbij
    -1.29
    是怎么回事
    -1.23
    を選択
    -1.16
    ところに
    -1.15
     naast
    -1.14
     longed
    -1.14
    を選び
    -1.14
     aperçu
    -1.13
    POSITIVE LOGITS
    がありますが
    1.40
    その
    1.26
    がある
    1.23
    CCIÓN
    1.14
     and
    1.13
    TRIBUN
    1.13
     nonetheless
    1.12
    があります
    1.08
    があるので
    1.06
     canh
    1.02
    Activations Density 0.005%

    No Known Activations