© 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. 103058
    Prev
    Next
    INDEX
    Explanations

    Charlottesville August 2017 tiki torches

    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
     Sanders
    -0.75
     antibodies
    -0.74
     Micros
    -0.73
    Melissa
    -0.73
    elles
    -0.73
     Gottes
    -0.72
     TES
    -0.72
    Sebagai
    -0.72
    بهترین
    -0.71
     Melissa
    -0.69
    POSITIVE LOGITS
     Charlottesville
    1.67
     Unite
    1.16
    lottesville
    1.09
    􏰀
    0.94
     August
    0.93
     tiki
    0.90
     Tiki
    0.88
    NOO
    0.87
     AUGUST
    0.85
    Char
    0.82
    Activations Density 0.019%

    No Known Activations