© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48521
    Prev
    Next
    INDEX
    Explanations

    terpene derivatives and Mondini dysplasia

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

    chemical compounds related to terpenes (like terpene, diterpene, sesquiterpene) in scientific texts.

    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
    ate
    -1.82
     facendo
    -1.80
    In
    -1.70
     essendo
    -1.61
     обеспечить
    -1.55
    縂
    -1.54
     zoude
    -1.52
    癱
    -1.48
    as
    -1.48
     devised
    -1.48
    POSITIVE LOGITS
    ↵↵
    1.98
    皤
    1.68
     mayoría
    1.59
     extraordinaire
    1.58
    ,\\
    1.55
    these
    1.52
    皞
    1.52
    tól
    1.51
     ваш
    1.50
    bringen
    1.48
    Activations Density 0.044%

    No Known Activations