© 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. 33344
    Prev
    Next
    INDEX
    Explanations

    silk and related fabrics

    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
     چسب
    -0.86
    聞いた
    -0.80
    Shallow
    -0.76
     crooked
    -0.72
     Wetlands
    -0.71
     loneliness
    -0.71
    Superintendent
    -0.70
     glue
    -0.68
    glue
    -0.68
     kawa
    -0.67
    POSITIVE LOGITS
    Silk
    1.43
     Silk
    1.41
     silk
    1.17
     satin
    1.07
    worms
    1.07
    ysm
    1.04
     Sil
    0.98
    silk
    0.97
    creen
    0.93
     Satin
    0.89
    Activations Density 0.006%

    No Known Activations