© 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. 119530
    Prev
    Next
    INDEX
    Explanations

    qualitative and quantitative descriptions

    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
     Herausforderung
    -1.48
     установка
    -1.48
     queridos
    -1.41
    lehem
    -1.41
     zweimal
    -1.40
     merkwür
    -1.39
     charming
    -1.38
     ohnehin
    -1.37
     [{
    -1.37
     เมื่อ
    -1.34
    POSITIVE LOGITS
     of
    2.11
     not
    1.55
     the
    1.52
     various
    1.48
     using
    1.48
     how
    1.47
     which
    1.45
     similar
    1.45
    علن
    1.43
     some
    1.41
    Activations Density 0.153%

    No Known Activations