© 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. 36783
    Prev
    Next
    INDEX
    Explanations

    where defines variables

    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
     آن‌ها
    0.42
     Pourquoi
    0.41
     primeiro
    0.41
     eerste
    0.41
     Reifen
    0.39
     pertama
    0.39
     first
    0.38
    ➝
    0.38
     Primeiro
    0.37
    Pourquoi
    0.37
    POSITIVE LOGITS
     '-'
    0.39
     '*'
    0.39
    roughly
    0.38
    ඹ
    0.38
     reflects
    0.37
    麽
    0.37
    ণু
    0.36
    𝒹
    0.36
     村
    0.36
     '.'
    0.36
    Activations Density 0.018%

    No Known Activations