© 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. 21879
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and definitions

    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
     Anſ
    -1.55
    kissen
    -1.36
     pourcentage
    -1.32
    튿
    -1.28
     obtenu
    -1.28
    necessarily
    -1.27
     inmig
    -1.27
     avaient
    -1.27
    был
    -1.26
    羮
    -1.26
    POSITIVE LOGITS
     or
    2.09
     like
    1.85
     even
    1.79
     only
    1.68
     both
    1.61
     beschränkt
    1.52
     under
    1.52
     out
    1.45
     solution
    1.43
     japonés
    1.43
    Activations Density 0.047%

    No Known Activations