© 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. 31-GEMMASCOPE-2-RES-262K
    7. 167668
    Prev
    Next
    INDEX
    Explanations

    greatest, best, image, design

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

    biotic and abiotic factors

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {//
    0.49
     وكانت
    0.48
    opatra
    0.42
    精力
    0.41
    {};
    0.41
    talk
    0.41
     dined
    0.41
    =$
    0.40
    inx
    0.40
    fledged
    0.40
    POSITIVE LOGITS
    Officers
    0.50
     FAILURE
    0.48
     высокие
    0.48
     NOTICE
    0.45
     usługi
    0.45
     Officers
    0.44
     ADMINISTR
    0.43
     vuelta
    0.43
     hick
    0.43
     Breeders
    0.41
    Activations Density 0.003%

    No Known Activations