© 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. 9280
    Prev
    Next
    INDEX
    Explanations

    flags and activity

    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
      
    -2.14
    ↵↵
    -1.97
     noved
    -1.88
    書いた
    -1.84
     sebagainya
    -1.72
    r
    -1.70
     inolvid
    -1.70
     вспомина
    -1.69
     unforeseen
    -1.68
     imprescindible
    -1.68
    POSITIVE LOGITS
    2
    2.05
     then
    1.98
    你的
    1.96
    洐
    1.88
    很少
    1.85
     cerdas
    1.84
     如
    1.83
     Resmi
    1.80
    4
    1.80
     内衣
    1.77
    Activations Density 0.013%

    No Known Activations