© 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. 60641
    Prev
    Next
    INDEX
    Explanations

    ratios and mappings

    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
    {
    -1.83
     allgemeine
    -1.76
     Gebruik
    -1.66
     {
    -1.63
    蛲
    -1.62
     étan
    -1.59
     sogenannte
    -1.59
     rè
    -1.59
                    
    -1.50
    Choosing
    -1.46
    POSITIVE LOGITS
     for
    1.62
     גם
    1.56
    ા
    1.56
    endimiento
    1.56
    through
    1.55
    because
    1.53
     myös
    1.52
     a
    1.52
    也能
    1.43
     with
    1.39
    Activations Density 0.015%

    No Known Activations