© 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. 90252
    Prev
    Next
    INDEX
    Explanations

    median calculation

    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
    ēj
    -0.86
     Rival
    -0.77
     Charms
    -0.75
    ttää
    -0.75
    karna
    -0.74
     Parsing
    -0.72
    fpm
    -0.72
    μένη
    -0.72
    Calidad
    -0.71
     Tobi
    -0.71
    POSITIVE LOGITS
     median
    2.06
    median
    1.70
    Median
    1.63
     Median
    1.52
     middle
    1.39
     mediana
    1.22
    middle
    1.17
     medi
    1.13
    Med
    1.08
     Med
    1.04
    Activations Density 0.015%

    No Known Activations