© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    rheumatic disorders or diseases

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

    scientific and technical terminology particularly from chemical, biological, and medical fields.

    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
    ي
    -3.17
    i
    -3.14
     he
    -2.88
    ি
    -2.80
    न
    -2.72
    I
    -2.67
    n
    -2.56
    ن
    -2.48
    ी
    -2.45
    ان
    -2.44
    POSITIVE LOGITS
    𐑂
    2.66
    いた
    2.53
    鏨
    2.50
    al
    2.48
    Interestingly
    2.39
    ⃙
    2.38
    杁
    2.36
    鼇
    2.36
     complacent
    2.34
     cantik
    2.33
    Activations Density 0.020%

    No Known Activations