© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91243
    Prev
    Next
    INDEX
    Explanations

    javascript `const` declarations

    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_34/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
     rése
    -1.73
     célè
    -1.69
     surpren
    -1.68
     parfüm
    -1.68
     éton
    -1.65
     dévou
    -1.64
     phénom
    -1.63
     histó
    -1.55
     sudadera
    -1.55
    麃
    -1.54
    POSITIVE LOGITS
     {
    2.78
     {
    2.39
     [
    2.39
     is
    2.14
    {
    2.08
     now
    1.82
     $
    1.81
     that
    1.68
    [
    1.65
    {
    1.59
    Activations Density 0.009%

    No Known Activations