© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7481
    Prev
    Next
    INDEX
    Explanations

    javadoc and code documentation

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

    The neuron detects Javadoc‐style documentation markers (e.g. “@inheritDoc” and “javadoc”).

    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
    <em>
    -2.20
    %;
    -2.11
    ～　
    -2.05
     vermutlich
    -2.05
    ３
    -1.93
    ９
    -1.86
    教你
    -1.80
    结语
    -1.79
     может
    -1.73
    ם
    -1.73
    POSITIVE LOGITS
    鉿
    2.34
    
    2.06
    鑁
    1.99
    
    1.98
    cieux
    1.90
     файлов
    1.90
    s
    1.89
    as
    1.89
     realizzazione
    1.84
    ementara
    1.80
    Activations Density 0.001%

    No Known Activations