© 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. 23180
    Prev
    Next
    INDEX
    Explanations

    ancient ruins and secrets

    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
    RAchievement
    0.45
     diversifying
    0.42
    汋
    0.39
     koch
    0.37
     constable
    0.36
     wyróż
    0.36
     hoş
    0.36
     Cloth
    0.36
    鰥
    0.36
    Squirrel
    0.36
    POSITIVE LOGITS
     ancient
    1.39
     древ
    1.29
     Ancient
    1.27
    Ancient
    1.27
    ancient
    1.27
    古代
    1.25
     ruins
    1.21
    遺跡
    1.14
     प्राचीन
    1.09
     archaeological
    1.09
    Activations Density 0.005%

    No Known Activations