© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33095
    Prev
    Next
    INDEX
    Explanations

    copper, ductility, lattice

    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
    лкой
    0.41
     التلاميذ
    0.39
    互联网档案馆
    0.38
     শুকনো
    0.38
     بای
    0.37
    balo
    0.37
    ᒧ
    0.37
     bioactive
    0.36
    ঝি
    0.36
    enegro
    0.36
    POSITIVE LOGITS
     Copper
    0.66
     copper
    0.64
    Copper
    0.62
     Lattice
    0.59
     ductility
    0.59
     crystal
    0.58
     vacancies
    0.57
    copper
    0.57
     lattice
    0.57
    銅
    0.56
    Activations Density 0.008%

    No Known Activations