© 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. 75295
    Prev
    Next
    INDEX
    Explanations

    seeing doctors or clinics

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

    phrases about patients seeing doctors or receiving medical care.

    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
     of
    -2.06
    亖
    -1.26
    栒
    -1.25
    𓆏
    -1.25
    situ
    -1.24
     terminer
    -1.24
     diverses
    -1.23
     petits
    -1.23
     ISLANDS
    -1.22
     abſ
    -1.22
    POSITIVE LOGITS
     ONLY
    1.56
     markedly
    1.44
     only
    1.43
     diminish
    1.42
    ⇰
    1.41
     TWO
    1.41
    著名的
    1.41
     decreased
    1.37
     new
    1.37
     Knowing
    1.36
    Activations Density 0.034%

    No Known Activations