© 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. 26488
    Prev
    Next
    INDEX
    Explanations

    html table and list tags

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

    This neuron activates strongly on HTML table structure tags (especially `<tr>` and `<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_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
     or
    -1.29
     also
    -1.12
     małe
    -1.10
     czarne
    -1.07
     arī
    -1.01
     powiedzieć
    -0.99
     también
    -0.98
     cię
    -0.98
     Lokales
    -0.95
    上次
    -0.95
    POSITIVE LOGITS
     *)__
    1.02
     محیط
    1.02
     restaura
    0.98
     risque
    0.97
    日を
    0.96
     gore
    0.95
     now
    0.95
     campe
    0.95
     rè
    0.92
    gruppen
    0.92
    Activations Density 0.009%

    No Known Activations