© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85751
    Prev
    Next
    INDEX
    Explanations

    factor VIII inhibitor

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

    numerical fractions represented as numbers with a slash (like 2/3, 7/8, etc.).

    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
     there
    -1.81
    </strong>
    -1.69
     if
    -1.62
     until
    -1.54
     last
    -1.53
     unless
    -1.52
     in
    -1.50
    上げて
    -1.47
    上がった
    -1.45
    until
    -1.42
    POSITIVE LOGITS
     not
    1.49
     stessi
    1.48
     解説
    1.45
     trochę
    1.41
    })$
    1.41
     alábbi
    1.40
    现在的
    1.40
    )$,
    1.38
    少し
    1.38
    )=
    1.36
    Activations Density 0.112%

    No Known Activations