© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1542
    Prev
    Next
    INDEX
    Explanations

    religious and philosophical texts

    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
     there
    -1.36
    念头
    -1.34
     pernic
    -1.33
     místě
    -1.31
    hassee
    -1.31
     hâm
    -1.30
    люсы
    -1.28
     who
    -1.28
     affirming
    -1.27
     krijg
    -1.25
    POSITIVE LOGITS
     about
    2.17
     of
    1.73
     I
    1.48
     more
    1.35
      
    1.35
     all
    1.32
     “
    1.28
     About
    1.28
     What
    1.27
     my
    1.24
    Activations Density 0.083%

    No Known Activations