© 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. 220854
    Prev
    Next
    INDEX
    Explanations

    information immediately, should expect

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

    every morning

    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
     dlg
    0.46
     ballot
    0.45
    합
    0.45
    카페
    0.43
    boxed
    0.43
    henyl
    0.42
     دسترس
    0.42
    机构
    0.42
     accessibles
    0.42
     ink
    0.41
    POSITIVE LOGITS
    悪い
    0.44
     kammam
    0.43
    næ
    0.42
    厲
    0.42
     beide
    0.41
     deewana
    0.41
     submar
    0.41
    勒
    0.40
     unfortunate
    0.40
    isca
    0.39
    Activations Density 0.001%

    No Known Activations