© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6593
    Prev
    Next
    INDEX
    Explanations

    Developer workflow & cycle time

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     所以
    0.38
    koliko
    0.38
    所以
    0.38
    𒌍
    0.38
    Donc
    0.37
    ваю
    0.36
     softmax
    0.36
     plaf
    0.36
     മറ്റൊരു
    0.36
    Databaze
    0.35
    POSITIVE LOGITS
    *
    0.38
    .’
    0.34
    ,,,,
    0.34
    </blockquote>
    0.34
     oors
    0.33
    ,,,
    0.33
    人都
    0.33
    •
    0.33
    ）』
    0.33
     Aline
    0.32
    Activations Density 0.230%

    No Known Activations