© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130214
    Prev
    Next
    INDEX
    Explanations

    Saving Private Ryan, Cast Away, Tom Brady

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    าค
    0.40
    يفة
    0.39
    謹
    0.38
    кі
    0.36
    жений
    0.36
     celeste
    0.36
     prudence
    0.36
    ()}
    0.36
    頸
    0.35
     holiness
    0.35
    POSITIVE LOGITS
     Brady
    0.47
     deflate
    0.47
     inflate
    0.42
     '='
    0.40
    (([
    0.38
    edian
    0.38
    どん
    0.38
     пере
    0.38
     জিজ্ঞাসাবাদ
    0.38
    čili
    0.38
    Activations Density 0.005%

    No Known Activations