© 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. 40018
    Prev
    Next
    INDEX
    Explanations

    years and budgets

    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
     various
    -1.62
     Nachdem
    -1.41
    .
    -1.38
    淖
    -1.36
     different
    -1.35
    <bos>
    -1.29
     spurred
    -1.28
     find
    -1.26
    ятся
    -1.26
     primeiras
    -1.24
    POSITIVE LOGITS
    %%%%%%%%%
    1.43
    nitř
    1.43
     mobiliario
    1.36
     completamente
    1.33
     opérés
    1.30
     amazingly
    1.29
    を
    1.29
    ’
    1.27
    borderSide
    1.27
     edition
    1.27
    Activations Density 0.108%

    No Known Activations