© 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-262K
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    subtly, an, someone, slightly, lifting

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    的感觉
    0.31
    杂志
    0.30
     Framing
    0.30
    سبوع
    0.29
    可谓
    0.29
     testAvg
    0.29
    疑问
    0.29
    胁
    0.28
     ആശ
    0.28
    琐
    0.28
    POSITIVE LOGITS
     rebuild
    0.36
    經濟
    0.35
     GDP
    0.35
     refinance
    0.35
    GDP
    0.34
     increases
    0.33
     macroeconomic
    0.33
     stabilizes
    0.32
    投資
    0.32
     reformed
    0.32
    Activations Density 0.001%

    No Known Activations