© 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. 31762
    Prev
    Next
    INDEX
    Explanations

    perspectives, trends, specialized, Melbourne

    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
    ลด
    0.50
    لب
    0.47
     خطر
    0.46
    لے
    0.45
    \
    0.45
    ดูก
    0.43
    ลก
    0.43
    ค
    0.42
    ampak
    0.42
    لت
    0.41
    POSITIVE LOGITS
     Yatha
    0.55
     уго
    0.49
     Полу
    0.49
    ным
    0.48
    ্টন
    0.48
     మో
    0.47
    ंडल
    0.47
    ocrite
    0.47
     Ян
    0.46
    mesini
    0.45
    Activations Density 0.018%

    No Known Activations