© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9059
    Prev
    Next
    INDEX
    Explanations

    distributed, incremental, sparse, probabilistic concepts

    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
     that
    -2.22
     ursprünglichen
    -2.03
     berühmten
    -2.00
     gewünschten
    -1.88
     ursprüng
    -1.80
     ДЛЯ
    -1.66
     betreffenden
    -1.65
     einzigartigen
    -1.65
     damaligen
    -1.65
     eigentlichen
    -1.65
    POSITIVE LOGITS
     menyen
    1.55
     stoff
    1.45
    f
    1.44
    your
    1.41
    you
    1.39
    the
    1.38
     and
    1.35
    і
    1.33
    (
    1.33
    and
    1.32
    Activations Density 0.214%

    No Known Activations