© 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. 34-GEMMASCOPE-RES-131K
    4. 107659
    Prev
    Next
    INDEX
    Explanations

    class names and code comments

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

    The neuron activates on PHPDoc/Javadoc‐style comment annotations (the “@…” tags and their surrounding docblock markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    public
    -1.00
     ?>/
    -0.94
     then
    -0.83
     войска
    -0.83
     zespo
    -0.82
     okazji
    -0.81
     acoged
    -0.80
     przet
    -0.80
     dniu
    -0.80
     trzec
    -0.78
    POSITIVE LOGITS
     class
    1.03
    class
    0.85
    TestClass
    0.84
     described
    0.83
     lớp
    0.81
    chiere
    0.80
     clase
    0.80
     Class
    0.79
     SPSS
    0.79
     eventuell
    0.79
    Activations Density 0.019%

    No Known Activations