© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8266
    Prev
    Next
    INDEX
    Explanations

    sand [followed by various words]

    np_acts-logits-general · gemini-2.5-flash-lite

    dust bunnies and motes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     средств
    0.40
    섯
    0.38
    💙
    0.38
    ゼ
    0.37
    槭
    0.37
    葲
    0.37
    さん
    0.37
    ☘
    0.36
    🥐
    0.36
    重ね
    0.36
    POSITIVE LOGITS
     sand
    0.96
     Sand
    0.89
    Sand
    0.88
    SAND
    0.83
    sand
    0.80
     SAND
    0.80
     dunes
    0.80
    沙
    0.79
     sandy
    0.77
     沙
    0.74
    Activations Density 0.100%

    No Known Activations