© 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. 22-GEMMASCOPE-RES-131K
    7. 14302
    Prev
    Next
    INDEX
    Explanations

    medical and scientific abbreviations

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

    scientific or technical terms, especially in fields like chemistry, biology, mathematics, and engineering.

    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_22/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
    ですが
    -1.48
     Hinsicht
    -1.48
    contd
    -1.44
     dessas
    -1.41
    ↵
    -1.38
     vienas
    -1.38
    phim
    -1.36
     этим
    -1.34
     viena
    -1.34
    Nguy
    -1.30
    POSITIVE LOGITS
    鹀
    1.78
     enthou
    1.63
     indien
    1.59
     humeur
    1.59
    饜
    1.55
     grec
    1.55
     aussit
    1.54
    mentable
    1.52
     triom
    1.49
     charmant
    1.49
    Activations Density 0.134%

    No Known Activations