© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78449
    Prev
    Next
    INDEX
    Explanations

    benchmarking computer performance

    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
     good
    -1.62
    good
    -1.27
    Good
    -1.01
    GOOD
    -0.97
     gute
    -0.92
     bonnes
    -0.84
     Good
    -0.83
     buena
    -0.83
    buon
    -0.80
     GOOD
    -0.80
    POSITIVE LOGITS
     benchmarks
    1.19
     benchmark
    1.13
     SPEC
    1.02
     workloads
    1.01
     kernels
    0.91
     applications
    0.89
     Livermore
    0.85
    SPEC
    0.84
    applications
    0.82
    polymer
    0.81
    Activations Density 0.032%

    No Known Activations