© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    following 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
     as
    -1.36
     TWO
    -1.34
    еру
    -1.32
     one
    -1.30
    writeHead
    -1.28
     on
    -1.28
     from
    -1.27
     июня
    -1.24
     WITH
    -1.23
     bzw
    -1.23
    POSITIVE LOGITS
     then
    1.77
     ausgewä
    1.59
     gegenwär
    1.46
    those
    1.38
     vielfach
    1.33
     puramente
    1.32
     gleicher
    1.30
    ⏑
    1.30
     spektak
    1.27
     niedrig
    1.27
    Activations Density 0.056%

    No Known Activations