© 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. 118040
    Prev
    Next
    INDEX
    Explanations

    originally, starts, then

    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
     cremallera
    -0.93
     bâtiments
    -0.89
     aéri
    -0.89
     liknande
    -0.88
     exportación
    -0.87
    dentro
    -0.87
    Сейчас
    -0.84
     unsplash
    -0.81
    比べると
    -0.81
    hline
    -0.81
    POSITIVE LOGITS
     in
    3.25
     to
    2.44
     initially
    2.13
     originally
    2.08
     initial
    1.93
     inicialmente
    1.83
     begin
    1.77
     originalmente
    1.76
     Initially
    1.76
     מל
    1.65
    Activations Density 0.031%

    No Known Activations