© 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. 137679
    Prev
    Next
    INDEX
    Explanations

    ancient chinese dynasties

    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
    Iron
    0.51
    铁
    0.48
     iron
    0.47
    iron
    0.46
    IRON
    0.46
    철
    0.43
     आयरन
    0.43
    鐵
    0.43
    Macro
    0.42
    钢铁
    0.42
    POSITIVE LOGITS
     tang
    0.50
     thigh
    0.44
     মার্ট
    0.43
     Shang
    0.42
     Contemporary
    0.41
     Tribe
    0.41
     clav
    0.41
     contemporary
    0.41
     CHO
    0.40
     tribe
    0.40
    Activations Density 0.005%

    No Known Activations