© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    async for

    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
    㗊
    0.42
    陏
    0.38
    鞑
    0.37
    Colorful
    0.37
    ذكر
    0.37
    ukiyoe
    0.36
     MODIFY
    0.36
    Disease
    0.36
     වැඩ
    0.36
    ﹝
    0.36
    POSITIVE LOGITS
     class
    0.40
     outputs
    0.39
     kron
    0.37
     ambient
    0.36
     registers
    0.36
     dramas
    0.35
     AVR
    0.35
     output
    0.34
     Kron
    0.34
     ration
    0.33
    Activations Density 0.005%

    No Known Activations