© 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. 10368
    Prev
    Next
    INDEX
    Explanations

    lipopolysaccharide

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

    non-English words or names, particularly from Asian, African, and European languages.

    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
     démocratique
    -1.87
    𔘓
    -1.84
    🢒
    -1.73
    荩
    -1.71
    懨
    -1.64
    屁股
    -1.62
    但在
    -1.62
    她也
    -1.59
     sembrano
    -1.58
    𐐪
    -1.56
    POSITIVE LOGITS
     of
    2.08
    </h4>
    1.82
    现在的
    1.75
     déterminé
    1.55
    astră
    1.53
    ).
    1.48
    ."
    1.48
    ,”
    1.48
    今年
    1.45
    imea
    1.45
    Activations Density 0.002%

    No Known Activations