© 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. 142656
    Prev
    Next
    INDEX
    Explanations

    thence, geographic directions

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

    purchasing and thriving

    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
    人の
    0.46
    人的
    0.46
    洨
    0.46
     người
    0.45
    時間
    0.45
    數學
    0.44
    大學
    0.44
    ικό
    0.44
    教
    0.44
    Luong
    0.43
    POSITIVE LOGITS
     renewed
    0.48
     خرید
    0.46
     kaufen
    0.43
     california
    0.43
    észet
    0.42
     stabilizer
    0.41
     rebate
    0.41
     актриса
    0.41
     obso
    0.40
     epilepsy
    0.40
    Activations Density 0.003%

    No Known Activations