© 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. 82
    Prev
    Next
    INDEX
    Explanations

    dates and titles

    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
    -1.44
     For
    -1.42
    usda
    -1.38
     webbplats
    -1.38
     for
    -1.38
    templateUrl
    -1.36
    ruguay
    -1.35
     on
    -1.35
     ficou
    -1.33
     что
    -1.32
    POSITIVE LOGITS
    1
    1.52
     ſaid
    1.47
     殼
    1.45
     Kristus
    1.41
    Parce
    1.41
     ftate
    1.37
     temen
    1.34
     火鍋
    1.34
    Réponse
    1.34
     struktur
    1.33
    Activations Density 0.014%

    No Known Activations