© 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. 19555
    Prev
    Next
    INDEX
    Explanations

    diseases and medical terms

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

    medical and scientific terminology related to diseases, conditions, and anatomical structures.

    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
     on
    -1.65
     at
    -1.37
     can
    -1.28
     for
    -1.19
    特定的
    -1.16
     giovane
    -1.15
    c
    -1.12
     diverse
    -1.11
     may
    -1.09
     in
    -1.08
    POSITIVE LOGITS
    すごく
    1.30
    spreis
    1.16
     prêmio
    1.14
     étaient
    1.13
    </b>
    1.07
     who
    1.07
     favoriser
    1.06
     aidé
    1.05
     Что
    1.05
     répondu
    1.02
    Activations Density 0.181%

    No Known Activations