© 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. 10-GEMMASCOPE-RES-131K
    7. 119628
    Prev
    Next
    INDEX
    Explanations

    unofficial status or de facto

    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
     plena
    -1.75
     ketika
    -1.69
     cuando
    -1.62
     touted
    -1.59
     When
    -1.57
     notable
    -1.56
    ．．．
    -1.52
    訛
    -1.51
    anderen
    -1.49
    ～～
    -1.45
    POSITIVE LOGITS
    ing
    1.82
    ’
    1.47
    +'</
    1.41
     gleiche
    1.41
    ′,
    1.40
    ”
    1.39
     selben
    1.39
    のかもしれません
    1.38
     Vergnügen
    1.38
     ehemalige
    1.38
    Activations Density 0.025%

    No Known Activations