© 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. 22-GEMMASCOPE-RES-131K
    7. 15382
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets

    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_22/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
     what
    -1.63
     their
    -1.52
    ‘
    -1.45
    ({
    -1.43
    ;
    -1.41
    {
    -1.41
     those
    -1.27
     espet
    -1.25
     find
    -1.23
    waitKey
    -1.23
    POSITIVE LOGITS
    Ingredienti
    1.77
    Preparazione
    1.60
    がありますが
    1.57
    Nasc
    1.52
    تحميل
    1.52
    Приготовление
    1.48
    <bos>
    1.47
    そういった
    1.45
    Torna
    1.45
     рома
    1.45
    Activations Density 0.001%

    No Known Activations