© 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. 66228
    Prev
    Next
    INDEX
    Explanations

    HTML encoding and doctypes

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

    The neuron fires on HTML‐related code constructs, i.e. HTML tags, DOCTYPE declarations, and related markup/encoding keywords.

    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
    ЧИ
    -0.89
    င
    -0.75
    лючение
    -0.75
    mug
    -0.74
    אור
    -0.72
     natürliche
    -0.71
     Umfeld
    -0.71
     Deviant
    -0.70
    ctics
    -0.70
     hilfreich
    -0.70
    POSITIVE LOGITS
    RQ
    0.83
    ឬ
    0.79
     新品
    0.78
     Delicious
    0.77
     seductive
    0.77
    体の
    0.76
    jev
    0.76
    ٧
    0.75
    сить
    0.74
    сть
    0.73
    Activations Density 0.067%

    No Known Activations