© 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. 38233
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
     imagined
    -0.85
     rumored
    -0.77
     Wag
    -0.76
     opini
    -0.76
     imig
    -0.75
    لينا
    -0.70
    roep
    -0.70
    шей
    -0.70
    brada
    -0.70
    level
    -0.69
    POSITIVE LOGITS
     rodzaju
    0.87
    的一次
    0.82
     meteen
    0.78
    őle
    0.77
     всеки
    0.76
     opět
    0.76
     Milestones
    0.76
    又一次
    0.76
     pieles
    0.75
    onesia
    0.75
    Activations Density 0.064%

    No Known Activations