© 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. 84356
    Prev
    Next
    INDEX
    Explanations

    dataset and benchmark

    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
     سي
    -0.83
     helps
    -0.81
     does
    -0.77
     begins
    -0.76
     outpost
    -0.72
     agua
    -0.72
     starts
    -0.71
     kỳ
    -0.71
    鷗
    -0.71
     blanket
    -0.70
    POSITIVE LOGITS
     dataset
    2.14
     datasets
    1.64
    dataset
    1.58
     benchmark
    1.54
    Dataset
    1.51
     Dataset
    1.47
    数据集
    1.38
     publicly
    1.30
     database
    1.21
     Benchmark
    1.19
    Activations Density 0.042%

    No Known Activations