© 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-65K
    7. 56359
    Prev
    Next
    INDEX
    Explanations

    steps and numbering

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Затем
    0.42
    然後
    0.40
    뿅
    0.39
    latent
    0.39
    squared
    0.38
     سپس
    0.38
    adding
    0.38
    測定
    0.37
    aminophen
    0.37
    arle
    0.37
    POSITIVE LOGITS
    瘘
    0.40
     substitute
    0.39
     είναι
    0.38
     sust
    0.38
     অবশ্য
    0.38
    Svg
    0.38
     alkyl
    0.38
    ベリー
    0.38
    SVG
    0.38
    Emails
    0.37
    Activations Density 0.011%

    No Known Activations