© 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. 70602
    Prev
    Next
    INDEX
    Explanations

    possibility, explanation, description

    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
               
    -1.04
     By
    -1.01
    -1.01
         
    -0.99
    })}
    -0.96
     продукти
    -0.95
             
    -0.95
     A
    -0.95
     G
    -0.94
     In
    -0.94
    POSITIVE LOGITS
     möglicherweise
    1.28
    Нам
    1.25
    Suka
    1.20
    Cinta
    1.18
    Penjelasan
    1.18
    Tentang
    1.16
    Fungsi
    1.13
    Возможно
    1.09
    Leírás
    1.09
     שונים
    1.06
    Activations Density 0.028%

    No Known Activations