© 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. 10-GEMMASCOPE-RES-131K
    7. 19403
    Prev
    Next
    INDEX
    Explanations

    documentation references and authors

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

    The main thing this neuron does is detect documentation‐style annotation tags in comments (e.g. Javadoc/PHPDoc/Rustdoc “@” tags).

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

    documentation-style annotation tags in source code comments (e.g., Doxygen/Javadoc/PHPDoc directives).

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

    references to documentation or related resources, particularly "@see" tags in code comments.

    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
    姈
    -2.30
    憷
    -2.06
    <bos>
    -1.90
    嘥
    -1.84
     considerados
    -1.80
     diversión
    -1.77
    擋
    -1.73
     usadas
    -1.71
    écoute
    -1.66
    矬
    -1.66
    POSITIVE LOGITS
     /
    2.64
     -
    1.98
     ratusan
    1.92
    it
    1.87
    hhhh
    1.84
     miliki
    1.84
    able
    1.78
     â
    1.73
    itées
    1.73
     '';
    1.71
    Activations Density 0.015%

    No Known Activations