© 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. 10-GEMMASCOPE-RES-131K
    4. 11257
    Prev
    Next
    INDEX
    Explanations

    et al. or abbreviation abbreviations

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

    This neuron detects the beginnings of bibliographic reference entries (author names followed by the publication year).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    author lists and related segments in scientific citations and bibliographic references.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    periods at the end of academic or scientific citation references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     tatuajes
    -2.08
     คา
    -2.05
     rése
    -1.98
     ralenti
    -1.98
     refroid
    -1.97
     apropiado
    -1.94
     medlemmer
    -1.93
     gracioso
    -1.91
     hermosos
    -1.91
     célè
    -1.88
    POSITIVE LOGITS
     in
    2.77
     from
    2.31
     to
    2.27
     This
    2.25
     so
    2.16
     If
    2.05
     by
    2.05
     at
    2.03
     for
    2.00
     Since
    1.96
    Activations Density 0.001%

    No Known Activations