© 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. 29111
    Prev
    Next
    INDEX
    Explanations

    myasthenia gravis

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

    names of medical conditions, particularly neurological and autoimmune diseases.

    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
     pérd
    -1.83
    —-
    -1.83
    也在
    -1.77
     oef
    -1.75
     vogel
    -1.73
     alfo
    -1.71
     rangs
    -1.67
     feo
    -1.66
     quoc
    -1.66
     bf
    -1.66
    POSITIVE LOGITS
     если
    1.95
     когда
    1.93
     даже
    1.82
     even
    1.74
     Это
    1.66
    ᳝
    1.63
    !”
    1.59
    )$
    1.58
    </sup>
    1.58
    𝗳
    1.55
    Activations Density 0.056%

    No Known Activations