© 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. 22020
    Prev
    Next
    INDEX
    Explanations

    UNESCO World Heritage site

    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
    ))}{
    0.47
    рог
    0.43
    ahanam
    0.39
     নিত
    0.38
     matrix
    0.38
    ष्टाचार
    0.37
     аксессу
    0.37
    squared
    0.37
    <0xB0>
    0.36
    ("/"))
    0.36
    POSITIVE LOGITS
     UNESCO
    2.38
    UNESCO
    2.19
     Unesco
    2.02
    联合国
    1.01
     listed
    0.93
    unes
    0.90
     Patrim
    0.85
     Patrimonio
    0.85
     designated
    0.84
     World
    0.84
    Activations Density 0.002%

    No Known Activations