© 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. 22-GEMMASCOPE-RES-131K
    7. 12622
    Prev
    Next
    INDEX
    Explanations

    numbers in code and math

    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_22/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
     sirop
    -1.52
     pistolet
    -1.43
     pantalon
    -1.43
     ananas
    -1.36
     hunde
    -1.36
     sapin
    -1.34
     capot
    -1.33
     savon
    -1.32
     flotte
    -1.31
     coussin
    -1.30
    POSITIVE LOGITS
     Also
    1.24
     This
    1.20
    ,
    1.18
     G
    1.16
    号線
    1.15
     In
    1.12
     By
    1.11
    :
    1.11
     nachher
    1.09
     J
    1.06
    Activations Density 0.021%

    No Known Activations