© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48839
    Prev
    Next
    INDEX
    Explanations

    stock market indices

    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
     生地
    -0.73
     expedition
    -0.69
     NATIONS
    -0.69
    𝗂
    -0.69
    知らない
    -0.68
     específicamente
    -0.68
     filmu
    -0.68
    batik
    -0.67
    お父
    -0.65
    Ranked
    -0.65
    POSITIVE LOGITS
     benchmark
    2.84
     benchmarks
    2.38
     index
    2.36
     indices
    2.31
    benchmark
    2.28
     indexes
    2.17
    Benchmark
    2.16
     Benchmark
    2.16
    index
    1.81
     Index
    1.73
    Activations Density 0.032%

    No Known Activations