© 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. 22-GEMMASCOPE-RES-131K
    7. 84299
    Prev
    Next
    INDEX
    Explanations

    list item start

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

    The neuron is strongly triggered by HTML list‐item elements (e.g. “<li>” tags and the word “item” in menu or list contexts).

    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
    jangan
    -1.00
     constr
    -0.98
     saan
    -0.97
     背包
    -0.94
     Kläger
    -0.92
     laissez
    -0.92
     évé
    -0.92
    terday
    -0.91
     美術
    -0.90
     集合
    -0.90
    POSITIVE LOGITS
    option
    1.17
    hline
    1.05
     option
    0.99
    bilities
    0.99
    +"&
    0.97
    ത്തി
    0.95
    getOption
    0.94
    nobyl
    0.94
     options
    0.94
    𓆟
    0.94
    Activations Density 0.002%

    No Known Activations