© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103537
    Prev
    Next
    INDEX
    Explanations

    Aur, Aurungzebe, Auroral, aurin

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

    words or word fragments that start with "Aur" or similar phonetic patterns.

    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
    鱨
    -2.53
     koncert
    -2.53
     cómod
    -2.38
    ⾄
    -2.33
     murieron
    -2.27
     صفحۀ
    -2.23
     motocicletas
    -2.22
     וכו
    -2.22
    他对
    -2.19
     tuviera
    -2.19
    POSITIVE LOGITS
    The
    3.34
    <i>
    3.14
    $
    3.02
    <em>
    2.66
    He
    2.56
    蔼
    2.45
    .
    2.44
    瓩
    2.33
    <h3>
    2.30
    In
    2.20
    Activations Density 0.000%

    No Known Activations