© 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. 22-GEMMASCOPE-RES-131K
    7. 98463
    Prev
    Next
    INDEX
    Explanations

    symptoms and conditions

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

    lists of symptoms or medical signs in healthcare 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_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
     kuni
    -1.30
     dani
    -1.11
    zną
    -1.11
     trd
    -1.08
     tph
    -1.07
    Ainsi
    -1.06
     kien
    -1.05
     kaban
    -1.03
     haki
    -1.03
    도록
    -1.03
    POSITIVE LOGITS
     or
    3.05
     или
    1.91
    或
    1.37
     یا
    1.33
     your
    1.31
     you
    1.31
     hoặc
    1.29
    または
    1.29
    ığınız
    1.23
    ないけど
    1.23
    Activations Density 0.026%

    No Known Activations