© 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. 87204
    Prev
    Next
    INDEX
    Explanations

    ## headings

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

    This neuron detects second-level section headings, i.e. H2 tags or their Markdown equivalents.

    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
    panjang
    -1.68
     Läs
    -1.64
    Fußball
    -1.64
     ingrained
    -1.63
     krás
    -1.60
    籥
    -1.57
    Legende
    -1.57
     detaylı
    -1.54
     září
    -1.53
     autobús
    -1.52
    POSITIVE LOGITS
     of
    1.97
    u
    1.92
    ing
    1.80
    h
    1.80
    ys
    1.64
    ere
    1.64
    in
    1.63
    鹇
    1.61
    ").
    1.61
    iner
    1.59
    Activations Density 0.003%

    No Known Activations