© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    take advantage

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

    only single output

    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
    毂
    0.45
    ীন্দ্র
    0.44
     devised
    0.43
     Wentworth
    0.42
     devising
    0.41
    衞
    0.41
     sillons
    0.41
     สน
    0.40
     }^{(
    0.40
     있어요
    0.39
    POSITIVE LOGITS
    Click
    0.48
    click
    0.43
    Enter
    0.43
     Enter
    0.41
    enter
    0.41
    select
    0.40
     Click
    0.40
     ввода
    0.40
    uggish
    0.40
    ianie
    0.39
    Activations Density 0.029%

    No Known Activations