© 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. 71479
    Prev
    Next
    INDEX
    Explanations

    years, volumes, pages

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

    The neuron selectively responds to numeric citation elements (e.g., volume, issue, year, and page numbers) in scientific reference entries.

    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
     would
    -1.56
     which
    -1.55
     and
    -1.42
     they
    -1.41
     should
    -1.40
     people
    -1.39
     that
    -1.35
     about
    -1.34
     During
    -1.29
     even
    -1.28
    POSITIVE LOGITS
    がありますが
    1.70
     nimmer
    1.59
     parfü
    1.53
    があるので
    1.50
    COMO
    1.46
    Seni
    1.44
     sacré
    1.38
    Jadi
    1.38
     faciliter
    1.36
     fluide
    1.34
    Activations Density 0.004%

    No Known Activations