© 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. 61473
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     is
    -2.83
     could
    -2.11
     would
    -2.09
    .
    -2.03
     of
    -2.00
     and
    -1.83
     have
    -1.65
     may
    -1.65
     i
    -1.64
     [
    -1.64
    POSITIVE LOGITS
    僕は
    1.88
     cewek
    1.75
    banez
    1.71
     kompatibel
    1.68
     palav
    1.67
    謌
    1.66
     hunde
    1.65
     suprême
    1.64
    箆
    1.64
     beijo
    1.62
    Activations Density 0.008%

    No Known Activations