© 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. 10-GEMMASCOPE-RES-131K
    4. 68879
    Prev
    Next
    INDEX
    Explanations

    website sections or pages

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

    This neuron detects mentions of a “section” (especially the “comments section” or similarly labeled parts of a page).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to website or publication subsections and interface areas, especially comment sections and threads.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "section" appearing in web page or forum contexts, particularly in phrases like "comment section," "reference section," or other navigational/organizational areas of websites.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Allemagne
    -1.83
     ヶ
    -1.66
    …?
    -1.57
    économ
    -1.55
    minecraftforge
    -1.54
     DataGridView
    -1.48
    𖤣
    -1.48
     découvrez
    -1.46
    verstanden
    -1.45
     and
    -1.44
    POSITIVE LOGITS
                  
    1.73
    -(
    1.58
    ="
    1.54
     of
    1.50
                 
    1.49
    í
    1.48
    ()
    1.47
                     
    1.46
                       
    1.46
    =-
    1.45
    Activations Density 0.020%

    No Known Activations