© 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. 22-GEMMASCOPE-RES-131K
    4. 39794
    Prev
    Next
    INDEX
    Explanations

    injuries and trauma

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

    descriptions of physical injuries and trauma to the body.

    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
     for
    -1.84
     that
    -1.67
     (
    -1.40
     this
    -1.37
     value
    -1.36
     at
    -1.33
     or
    -1.27
     unless
    -1.25
     подобрать
    -1.19
    !
    -1.19
    POSITIVE LOGITS
    erdings
    1.34
    walde
    1.32
    Удачи
    1.31
     camioneta
    1.29
    cookieParser
    1.27
    ༎
    1.22
     })
    
    1.20
    >--}}
    1.20
    复杂的
    1.19
     ดี
    1.17
    Activations Density 0.021%

    No Known Activations