© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71562
    Prev
    Next
    INDEX
    Explanations

    abbreviations for medical conditions and imaging techniques

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

    medical and scientific abbreviations or acronyms in parentheses.

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

    This neuron fires strongly on parenthetical expressions—especially acronyms or numbers enclosed in parentheses.

    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
     of
    -1.80
     on
    -1.57
    aphthalene
    -1.27
    attività
    -1.16
    ของ
    -1.15
    corpions
    -1.10
     của
    -1.09
     where
    -1.06
     extenso
    -1.05
     suficiente
    -1.04
    POSITIVE LOGITS
     такие
    1.17
     empêcher
    1.14
     such
    1.11
    beelden
    1.08
    他にも
    1.06
    égio
    1.05
     oignon
    1.02
    🚀
    1.01
     Currents
    1.01
     таких
    1.00
    Activations Density 0.183%

    No Known Activations