© 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. 10-GEMMASCOPE-RES-131K
    7. 85430
    Prev
    Next
    INDEX
    Explanations

    HTML/code tags

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

    The neuron strongly activates on HTML table cell tags (the `<TD …>` elements).

    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
     multifaceted
    -3.31
     exquisitely
    -3.19
     nearing
    -3.17
     meticulously
    -3.17
     resolute
    -3.14
     unrelenting
    -3.05
     intricacies
    -3.00
     enormously
    -2.97
     weirdly
    -2.95
     supremely
    -2.94
    POSITIVE LOGITS
     they
    2.75
    怱
    2.58
     Provides
    2.58
     และ
    2.53
    鸸
    2.50
     zoude
    2.48
    栳
    2.45
     mê
    2.42
     uniquement
    2.41
     decidedly
    2.39
    Activations Density 0.001%

    No Known Activations