© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26166
    Prev
    Next
    INDEX
    Explanations

    ancient Mesopotamian civilizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    medieval
    0.57
    Medieval
    0.55
    ৤
    0.53
     medieval
    0.45
     مسلم
    0.43
     Medieval
    0.42
     بنگالی
    0.41
    ཊ
    0.41
    聚集
    0.41
    chets
    0.40
    POSITIVE LOGITS
     Mesopot
    1.04
     Babylonian
    1.04
     Sumer
    0.96
     Assy
    0.94
     Mesopotamia
    0.89
     Babylon
    0.86
     Hitt
    0.84
     Ugar
    0.84
     Akk
    0.79
     Iraq
    0.77
    Activations Density 0.012%

    No Known Activations