© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35182
    Prev
    Next
    INDEX
    Explanations

    sophisticated civilizations and culture

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    古代
    0.47
     Anci
    0.47
    Ancient
    0.46
     ancients
    0.46
     antiquity
    0.46
     Antiqu
    0.45
     Afghan
    0.44
    古
    0.44
     ancient
    0.43
     Tweet
    0.43
    POSITIVE LOGITS
     architecture
    0.82
     metallurgy
    0.77
     Architecture
    0.73
     arquitectura
    0.71
     cuisine
    0.71
     arquitet
    0.71
     artistry
    0.70
    architecture
    0.68
    建築
    0.68
     philosophy
    0.67
    Activations Density 0.005%

    No Known Activations