© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47243
    Prev
    Next
    INDEX
    Explanations

    . prod guides track

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

    The neuron fires on tokens that are metadata keys (especially those with underscores) in YAML frontmatter—e.g. “localization_”, “doc_”, “ms”, and similar field names.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     sehr
    -0.95
    ਾਨ
    -0.94
    ഔ
    -0.93
     with
    -0.87
    توض
    -0.87
     darbu
    -0.86
     dataList
    -0.85
    内心
    -0.83
     but
    -0.83
     from
    -0.83
    POSITIVE LOGITS
    Original
    1.01
    Literatuur
    1.00
    ignore
    0.96
     แท
    0.92
     Original
    0.92
     original
    0.91
    attached
    0.86
    original
    0.86
    mh
    0.84
     RequestMethod
    0.83
    Activations Density 0.078%

    No Known Activations