© 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. 22-GEMMASCOPE-RES-131K
    4. 68858
    Prev
    Next
    INDEX
    Explanations

    free item or offer

    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
    ,
    -1.44
     
    -1.16
     Sheeran
    -1.01
     любы
    -0.97
     detalladas
    -0.94
    渍
    -0.94
    いただく
    -0.93
    comings
    -0.93
    гию
    -0.93
     itself
    -0.93
    POSITIVE LOGITS
     each
    1.80
    每个
    1.27
    各自
    1.23
    他们
    1.21
    Opin
    1.20
     their
    1.16
    もしれません
    1.16
     jejich
    1.15
    ﺀ
    1.14
    每個
    1.09
    Activations Density 0.025%

    No Known Activations