© 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. 22-GEMMASCOPE-RES-131K
    7. 13913
    Prev
    Next
    INDEX
    Explanations

    medical and sports abbreviations

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

    medical and scientific abbreviations in parentheses.

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

    The neuron fires on the opening parenthesis of parenthetical abbreviations or acronyms (e.g., “(ECM)”, “(ICU)”), marking where an acronym is being introduced.

    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
    kleid
    -1.16
     męska
    -1.13
     kobieta
    -1.10
     gehör
    -1.10
    どうしよう
    -1.08
    摀
    -1.08
    えっ
    -1.07
    踝
    -1.05
    メラ
    -1.04
     zimowa
    -1.03
    POSITIVE LOGITS
     for
    1.20
     while
    1.19
     during
    1.09
     through
    1.05
     many
    1.03
     when
    1.02
     often
    0.92
     although
    0.91
     may
    0.91
     mangel
    0.88
    Activations Density 0.273%

    No Known Activations