© 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. 76178
    Prev
    Next
    INDEX
    Explanations

    authors of mathematical papers

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

    The neuron is picking out citation and reference markers (e.g. section numbers, “See …”, arXiv links, author names, “abstract:”, etc.) indicating bibliographic or cross‐reference material.

    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
    teel
    -0.76
    踐
    -0.69
     Carnival
    -0.69
     касается
    -0.69
     Owner
    -0.69
     Nashville
    -0.68
     Konf
    -0.68
    ۢ
    -0.67
     Arce
    -0.67
     Perth
    -0.67
    POSITIVE LOGITS
    Rings
    1.06
     Rings
    1.02
    Algebra
    0.90
     rings
    0.84
     racks
    0.79
     Zappa
    0.78
    AMS
    0.77
     GAP
    0.75
    algebra
    0.75
    rings
    0.75
    Activations Density 0.076%

    No Known Activations