© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30339
    Prev
    Next
    INDEX
    Explanations

    words starting with lipo

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

    Eastern European or scientific surnames, particularly when followed by professional or academic titles.

    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_34/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
     determined
    -0.79
    我們的
    -0.76
     significant
    -0.75
     such
    -0.75
     plead
    -0.73
     называют
    -0.68
     determine
    -0.68
     哥
    -0.68
     literally
    -0.68
    فاء
    -0.68
    POSITIVE LOGITS
    repo
    0.99
    UPO
    0.89
    FUTURE
    0.80
    有可能
    0.79
    artikel
    0.79
    issaient
    0.75
    ంత
    0.74
     spo
    0.74
    gerne
    0.74
    UBER
    0.74
    Activations Density 0.073%

    No Known Activations