© 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. 80864
    Prev
    Next
    INDEX
    Explanations

    providing multiple modules

    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
     plát
    -0.90
     RIGHTS
    -0.88
     Органи
    -0.87
     siden
    -0.87
     selam
    -0.86
    
    -0.86
    beten
    -0.86
     NATIONS
    -0.84
    isiä
    -0.82
     Temos
    -0.80
    POSITIVE LOGITS
     provide
    1.20
     provides
    1.02
    provide
    0.93
     providing
    0.88
     Provide
    0.86
     contribute
    0.86
    тины
    0.85
     Provides
    0.83
     anbieten
    0.80
     предоставля
    0.80
    Activations Density 0.002%

    No Known Activations