© 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. 319
    Prev
    Next
    INDEX
    Explanations

    years 2020-2050

    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
    !”
    -1.79
     включает
    -1.66
     corrobor
    -1.66
     necessitates
    -1.59
     обеспечивает
    -1.58
    -”
    -1.56
     mani
    -1.55
     hundred
    -1.54
     quell
    -1.53
    ched
    -1.52
    POSITIVE LOGITS
     they
    1.56
    家乡
    1.50
    They
    1.49
    他们
    1.48
    一个
    1.43
     $
    1.43
     "
    1.37
    ،
    1.34
     แต่
    1.34
    You
    1.34
    Activations Density 0.005%

    No Known Activations