© 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. 34-GEMMASCOPE-RES-131K
    7. 108821
    Prev
    Next
    INDEX
    Explanations

    `notice` and `dev` comments

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

    The neuron is selectively activating on code‐annotation tokens—primarily the “@” annotation marker in comments and the “pragma” preprocessor directive.

    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
     Collab
    -0.78
     alleen
    -0.77
    ТЕЛЬ
    -0.76
    ثي
    -0.75
    滁
    -0.75
     μπορεί
    -0.75
    ЩЕ
    -0.73
    vering
    -0.72
    اشت
    -0.71
    āci
    -0.71
    POSITIVE LOGITS
    notice
    1.66
     notice
    1.59
    dev
    1.46
     Notice
    1.24
     NOTICE
    1.23
     dev
    1.19
    Notice
    1.18
    NOTICE
    1.08
     Dev
    1.00
    Notices
    0.95
    Activations Density 0.002%

    No Known Activations