© 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. 38
    Prev
    Next
    INDEX
    Explanations

    we look forward to

    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
     about
    -1.55
    躥
    -1.51
     renfer
    -1.48
     gänzlich
    -1.45
     véhic
    -1.39
    囔
    -1.39
    new
    -1.35
     plötzlich
    -1.34
     امروز
    -1.33
     sosteniendo
    -1.33
    POSITIVE LOGITS
     will
    1.71
     hope
    1.69
     your
    1.65
     you
    1.55
     each
    1.54
     він
    1.38
     this
    1.34
     каждую
    1.34
     considération
    1.34
     of
    1.33
    Activations Density 0.032%

    No Known Activations