© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40074
    Prev
    Next
    INDEX
    Explanations

    name="attribute" assignments

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

    The neuron is triggered by XML/HTML tag attributes—especially the attribute names (like “name,” “class,” “id,” etc.) and their associated values.

    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
     from
    -1.77
     in
    -1.73
     any
    -1.68
     because
    -1.57
     within
    -1.51
     during
    -1.49
     just
    -1.48
     when
    -1.43
     and
    -1.42
     using
    -1.39
    POSITIVE LOGITS
     wondrous
    1.82
     magnificent
    1.66
     gigantic
    1.53
     momentous
    1.53
     ludicrous
    1.52
     alluring
    1.50
     marvelous
    1.49
     unending
    1.48
     majestic
    1.48
     quintessential
    1.45
    Activations Density 0.007%

    No Known Activations