© 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. 39274
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions and equations

    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
     turista
    -1.41
     tragé
    -1.30
     הייתה
    -1.24
         
    -1.23
     MUCH
    -1.23
    ışık
    -1.22
                      
    -1.21
     doubtless
    -1.20
    逮捕
    -1.20
     rebuild
    -1.19
    POSITIVE LOGITS
    ↵
    1.58
     deoarece
    1.28
     cercanas
    1.24
    仉
    1.23
     aisladas
    1.21
     eléctricas
    1.20
    ۴
    1.19
     móc
    1.19
     mediados
    1.18
     comienzos
    1.15
    Activations Density 0.274%

    No Known Activations