© 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. 10-GEMMASCOPE-RES-131K
    7. 112891
    Prev
    Next
    INDEX
    Explanations

    technical and medical terms

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

    The neuron detects abbreviated medical/scientific terminology, particularly "i.p." (intraperitoneal), "p.o." (per oral), and "brainstem" in scientific and medical literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    艄
    -2.00
    看一下
    -2.00
     \
    -1.98
    ￪
    -1.95
    ᯾
    -1.92
    ⚌
    -1.92
     sembl
    -1.89
    erráneo
    -1.88
    チーフ
    -1.82
     โดย
    -1.81
    POSITIVE LOGITS
    ?”
    1.98
    灕
    1.93
     and
    1.87
    一惊
    1.83
     adhesivo
    1.77
    
    1.76
    我們
    1.74
     These
    1.73
    1
    1.73
     Focusing
    1.70
    Activations Density 0.031%

    No Known Activations