© 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. 65422
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     THOSE
    -1.63
     manguera
    -1.62
     consommer
    -1.55
     takimi
    -1.54
     introducir
    -1.52
     dibujado
    -1.42
     einzeln
    -1.42
    􏰁
    -1.41
     sellado
    -1.41
     Aktual
    -1.40
    POSITIVE LOGITS
     to
    2.77
     for
    2.17
     of
    2.08
     because
    2.03
     since
    1.87
     or
    1.72
     any
    1.70
     most
    1.63
     when
    1.59
     some
    1.58
    Activations Density 0.118%

    No Known Activations