© 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. 139819
    Prev
    Next
    INDEX
    Explanations

    ice sheets

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

    turns out, atmospheric, quietly

    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
     슈
    0.51
    zinha
    0.45
     اختيار
    0.44
     ち
    0.43
     Clustering
    0.43
     صہیونی
    0.41
     フリー
    0.41
    转化
    0.41
     活動
    0.41
    🆙
    0.41
    POSITIVE LOGITS
    र्नर
    0.50
    可靠
    0.49
     sugary
    0.45
     pemilik
    0.45
    ecek
    0.45
     unreliable
    0.44
    inspect
    0.44
    жаем
    0.44
    ur
    0.44
    Larry
    0.44
    Activations Density 0.000%

    No Known Activations