© 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. 216037
    Prev
    Next
    INDEX
    Explanations

    about, as, every, some, highest

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

    identifying concluding "ing" words

    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
    ت
    0.55
    انت
    0.55
    ી
    0.55
    確実に
    0.52
    琍
    0.52
    გილ
    0.52
    াভাব
    0.50
    ل
    0.50
    歌
    0.50
    載
    0.50
    POSITIVE LOGITS
     Schwartz
    0.49
     Schwarzschild
    0.47
     Stras
    0.47
     Bursa
    0.47
     Burke
    0.47
     Phelps
    0.46
     Dempsey
    0.46
     তদ
    0.46
     MEM
    0.46
     Swann
    0.45
    Activations Density 0.000%

    No Known Activations