© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123524
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and chemical compounds

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

    medical and scientific terminology related to blood tests and measurements.

    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
    .
    -1.57
    7
    -1.40
     asegurarse
    -1.40
    鴣
    -1.38
    2
    -1.38
    鯪
    -1.34
     스톡
    -1.31
    Descrizione
    -1.31
     noticeable
    -1.30
     subtly
    -1.30
    POSITIVE LOGITS
     a
    2.59
     distintos
    1.59
     příslu
    1.56
     販売
    1.55
     différentes
    1.55
    </sub>
    1.48
    mentable
    1.47
    女孩子
    1.45
     memutus
    1.41
    VD
    1.41
    Activations Density 0.112%

    No Known Activations