© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60567
    Prev
    Next
    INDEX
    Explanations

    document type declaration

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find markup declaration openings starting with “<!” (e.g. DOCTYPE or comment starts).

    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
    ляции
    -2.31
     Hoje
    -2.22
    揶
    -2.11
    みたいです
    -2.09
     aynı
    -2.09
     teratur
    -2.05
     또
    -2.03
    訛
    -2.03
    镚
    -2.02
     participan
    -2.00
    POSITIVE LOGITS
    1
    3.25
    9
    2.50
    4
    2.44
    8
    2.38
     оружия
    2.34
    ان
    2.31
    很
    2.28
    ,,,,
    2.27
    ль
    2.25
    ка
    2.20
    Activations Density 0.005%

    No Known Activations