© 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. 34-GEMMASCOPE-RES-131K
    7. 118286
    Prev
    Next
    INDEX
    Explanations

    redistribution and .NET Framework

    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_34/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
     LTE
    -0.78
     テ
    -0.75
     després
    -0.74
    皮
    -0.73
     soutě
    -0.71
    妮
    -0.71
    ],'
    -0.71
    ஹ
    -0.69
     SG
    -0.69
     juvenile
    -0.69
    POSITIVE LOGITS
     Redist
    1.61
     redistribute
    1.31
     redistribution
    1.26
    distribu
    1.00
    redi
    0.98
     runtime
    0.96
     Runtime
    0.95
     distribu
    0.89
     Distribu
    0.88
     إعادة
    0.88
    Activations Density 0.068%

    No Known Activations