© 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. 118946
    Prev
    Next
    INDEX
    Explanations

    questions and specific entities

    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
    不过是
    -1.80
     tornou
    -1.72
     criou
    -1.70
     It
    -1.63
     igreja
    -1.55
     особенно
    -1.55
    是一個
    -1.53
     recebeu
    -1.52
     llegó
    -1.52
     становится
    -1.52
    POSITIVE LOGITS
     where
    1.96
     which
    1.90
     that
    1.68
    屛
    1.65
     when
    1.63
    	
    1.55
     such
    1.49
    𝘦
    1.49
     )}$
    1.48
    躥
    1.45
    Activations Density 0.000%

    No Known Activations