© 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. 73346
    Prev
    Next
    INDEX
    Explanations

    birth and death dates in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.23
    <h2>
    -1.20
    trät
    -1.17
     Parent
    -1.17
     remedy
    -1.16
    if
    -1.15
    ۔
    -1.13
    ਗ਼
    -1.11
     objected
    -1.09
     выбрать
    -1.09
    POSITIVE LOGITS
     tén
    1.42
     avez
    1.38
     phénom
    1.34
     avons
    1.32
     becauſe
    1.30
    ність
    1.30
     ahora
    1.30
    📥
    1.25
     devenue
    1.23
     blieben
    1.23
    Activations Density 0.093%

    No Known Activations