© 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. 10-GEMMASCOPE-RES-131K
    7. 13317
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations

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

    medical and scientific acronyms or abbreviations, particularly in parentheses.

    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
     can
    -1.56
     It
    -1.29
    嗚
    -1.26
     zamiast
    -1.23
     вважа
    -1.21
     has
    -1.20
    何故
    -1.17
     was
    -1.16
     варіан
    -1.13
    Ambos
    -1.13
    POSITIVE LOGITS
    fordshire
    1.55
    righted
    1.51
     huset
    1.48
    まって
    1.38
    entially
    1.31
    iiiiiiii
    1.30
    CLING
    1.28
    ksyon
    1.27
    }_{
    1.26
    NÉ
    1.25
    Activations Density 0.313%

    No Known Activations