© 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. 41874
    Prev
    Next
    INDEX
    Explanations

    discrete 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
    .
    -1.52
    ühner
    -1.31
     serão
    -1.31
     mientras
    -1.30
     cuyos
    -1.28
     to
    -1.23
     gebruiken
    -1.22
     tři
    -1.22
     tendrá
    -1.21
     relacionado
    -1.21
    POSITIVE LOGITS
     this
    1.77
     it
    1.67
     there
    1.54
     then
    1.46
     that
    1.43
     their
    1.34
     both
    1.28
     very
    1.23
    本日の
    1.16
     promoting
    1.15
    Activations Density 0.210%

    No Known Activations