© 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. 81093
    Prev
    Next
    INDEX
    Explanations

    optimized technical implementations

    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
    bdd
    -0.78
     vroeg
    -0.77
    enas
    -0.77
    刪
    -0.76
    ження
    -0.74
     shoes
    -0.73
    xml
    -0.71
     preacher
    -0.70
     gezondheid
    -0.69
    lccccc
    -0.69
    POSITIVE LOGITS
    specialized
    1.14
     slower
    1.13
     optimized
    1.10
     slow
    1.09
     faster
    1.08
    Slow
    1.06
     specialized
    1.05
    Optimized
    1.03
    optimized
    1.02
    slow
    1.01
    Activations Density 0.110%

    No Known Activations