© 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. 67292
    Prev
    Next
    INDEX
    Explanations

    more than, more variants

    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
    ↵↵
    -2.97
     {
    -2.73
     et
    -2.61
    {
    -2.42
     somewhat
    -2.39
     tremendous
    -2.31
    銠
    -2.31
    桕
    -2.31
     evita
    -2.31
     immense
    -2.27
    POSITIVE LOGITS
    there
    2.52
    that
    2.41
    vantaged
    2.39
    ୌ
    2.36
    when
    2.36
    
    2.28
    While
    2.25
     دیکھیے
    2.25
    Many
    2.23
    vão
    2.23
    Activations Density 0.002%

    No Known Activations