© 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. 21294
    Prev
    Next
    INDEX
    Explanations

    still continuing

    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
    Dès
    -1.33
     since
    -1.30
    ار
    -1.28
    Dés
    -1.27
    ется
    -1.27
    Теперь
    -1.26
    舠
    -1.26
    После
    -1.21
    Voilà
    -1.20
    Produtos
    -1.20
    POSITIVE LOGITS
    and
    1.23
     QUÉ
    1.21
    ActionCreators
    1.20
    H
    1.20
    movie
    1.20
    内の
    1.18
    lıkla
    1.18
    शत
    1.18
     detalles
    1.17
     NATIONAL
    1.17
    Activations Density 0.047%

    No Known Activations