© 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. 23892
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and 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
     pomen
    -1.35
    рна
    -1.34
    They
    -1.29
    🌸
    -1.28
    只要
    -1.28
     antara
    -1.25
    ↵↵↵
    -1.24
    什么
    -1.23
    也很
    -1.22
     CONCEPTS
    -1.22
    POSITIVE LOGITS
     verschillende
    1.73
     the
    1.66
     are
    1.58
     to
    1.57
     wybran
    1.52
     acoged
    1.51
     różnych
    1.47
    those
    1.45
     einwand
    1.43
     bestens
    1.41
    Activations Density 0.182%

    No Known Activations