© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65010
    Prev
    Next
    INDEX
    Explanations

    communication, medical, and technology terms

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

    scientific and technical terms from various fields including medicine, biology, technology, and engineering.

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

    The neuron fires on specialized technical or scientific terminology—particularly multi‐letter acronyms and complex biomedical or engineering terms (e.g. “syndrome,” “apoptosis,” “IGBT”).

    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
    Apparatus
    -1.04
     clásico
    -1.02
    䊏
    -1.01
    trze
    -0.98
     levert
    -0.98
     clásicos
    -0.97
     oposición
    -0.97
    vinger
    -0.96
    欅
    -0.96
    进攻
    -0.95
    POSITIVE LOGITS
    recent
    1.15
    recently
    1.12
     or
    0.99
     zoll
    0.97
    ３
    0.96
    越来越
    0.96
     currently
    0.96
    ઘ
    0.96
    今日も
    0.95
    TF
    0.94
    Activations Density 0.332%

    No Known Activations