© 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. 34-GEMMASCOPE-RES-131K
    7. 31371
    Prev
    Next
    INDEX
    Explanations

    publisher names, years, and locations

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

    The main thing this neuron does is spot bibliographic citation elements (author names, years, parentheses, commas, volume/page numbers).

    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
    One
    -1.00
     =>'
    -0.98
     sulit
    -0.97
     one
    -0.96
     this
    -0.94
     ostensibly
    -0.93
    Both
    -0.93
    七年
    -0.93
     Ministro
    -0.92
     epitom
    -0.92
    POSITIVE LOGITS
     Springer
    1.30
     else
    1.05
     CRC
    0.98
     John
    0.98
     trám
    0.95
     McGraw
    0.94
    árny
    0.94
     Elsevier
    0.93
     Prentice
    0.93
    aws
    0.92
    Activations Density 0.006%

    No Known Activations