© 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. 22-GEMMASCOPE-RES-131K
    4. 13723
    Prev
    Next
    INDEX
    Explanations

    medical citations and numbers

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

    citation references in academic papers, particularly author names followed by "et al." and reference numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects punctuation marks and numeric citation/reference tokens (commas, periods, colons, semicolons, and citation 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_22/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
     掃除
    -1.98
     chré
    -1.63
     パソコン
    -1.52
     filós
    -1.31
     to
    -1.31
     bangun
    -1.30
     муки
    -1.30
    =============
    -1.27
    ","\
    -1.27
    世间
    -1.26
    POSITIVE LOGITS
    ּוֹ
    1.90
    ִּ
    1.87
    ֶּ
    1.84
    ַּ
    1.82
    ְּ
    1.67
    ֵּ
    1.59
     clinical
    1.48
    ˒
    1.48
     review
    1.48
     patients
    1.47
    Activations Density 0.109%

    No Known Activations