© 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-65K
    7. 31479
    Prev
    Next
    INDEX
    Explanations

    cheesecake, pursuing passions, Hanukkah

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ون
    0.49
    小
    0.49
     وبين
    0.45
    คุณ
    0.44
     выборе
    0.43
    Colorado
    0.43
    เพิ่ม
    0.43
    هرات
    0.43
    สวย
    0.42
     cinquième
    0.42
    POSITIVE LOGITS
     प्रक्रिया
    0.48
     দিয়াছেন
    0.47
    gger
    0.47
    QB
    0.47
    𝘿
    0.44
    descriptor
    0.43
     touchdowns
    0.43
     化粧
    0.42
     특집
    0.42
     त्व
    0.42
    Activations Density 0.003%

    No Known Activations