© 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. 741
    Prev
    Next
    INDEX
    Explanations

    class names followed by nouns

    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
     regresó
    -1.00
     nasel
    -1.00
     balón
    -0.96
     its
    -0.95
    nasel
    -0.94
     Thee
    -0.94
     participaron
    -0.94
    tarta
    -0.93
     trabajó
    -0.92
     cerró
    -0.92
    POSITIVE LOGITS
    ()
    1.17
    (){
    1.12
    ():
    1.02
    (@
    0.95
     ребен
    0.91
     производство
    0.90
    𝑔
    0.89
     ソース
    0.88
    ล์
    0.87
     часть
    0.84
    Activations Density 0.024%

    No Known Activations