© 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. 10-GEMMASCOPE-RES-131K
    7. 66851
    Prev
    Next
    INDEX
    Explanations

    scientific and medical findings

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

    enumeration markers in scientific and technical text like numbered lists, points, or sections.

    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
    %;
    -1.70
     is
    -1.66
     a
    -1.51
    ｃ
    -1.49
     I
    -1.39
    fgaben
    -1.38
     an
    -1.37
    ercizi
    -1.36
    economic
    -1.34
     allerdings
    -1.34
    POSITIVE LOGITS
    اقرأ
    1.59
    後で
    1.58
    感じが
    1.47
     overall
    1.47
    المصدر
    1.45
     thanks
    1.45
    création
    1.44
     because
    1.41
     podían
    1.41
     cantora
    1.39
    Activations Density 0.071%

    No Known Activations