© 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. 102285
    Prev
    Next
    INDEX
    Explanations

    do so as

    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
    quelles
    -1.62
    髣
    -1.59
     vielfach
    -1.34
     brevemente
    -1.33
     eene
    -1.29
    ༣
    -1.28
     mmm
    -1.26
    嘮
    -1.26
    心头
    -1.26
     zijne
    -1.26
    POSITIVE LOGITS
     then
    1.70
     will
    1.66
     at
    1.41
     or
    1.38
     and
    1.38
     као
    1.34
     in
    1.33
     take
    1.29
     without
    1.27
     ће
    1.23
    Activations Density 0.144%

    No Known Activations