© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41236
    Prev
    Next
    INDEX
    Explanations

    ncbi, pubmed, genbank

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

    The neuron detects references to scientific databases, particularly NCBI, PubMed, and GenBank.

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

    The neuron detects mentions of major biomedical data repositories (e.g. “NCBI,” “PubMed,” and related database URLs).

    oai_token-act-pair · o4-miniTriggered 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
    zędu
    -2.53
    ization
    -2.50
    haviours
    -2.47
    蟥
    -2.45
    ătate
    -2.28
    卹
    -2.23
    ねー
    -2.23
     terwijl
    -2.22
    ⫸
    -2.17
    gebras
    -2.16
    POSITIVE LOGITS
    '
    3.31
    t
    2.50
     \
    2.44
    with
    2.42
    蹋
    2.34
     neue
    2.33
    te
    2.31
    B
    2.27
    ↵
    2.17
     three
    2.13
    Activations Density 0.002%

    No Known Activations