© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43822
    Prev
    Next
    INDEX
    Explanations

    Masonic symbolism

    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/layer_31_width_262k_l0_medium
    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
    狸
    0.43
     speakers
    0.41
     продажи
    0.38
     geschikt
    0.38
    šnj
    0.38
     fiyat
    0.38
     coch
    0.37
     SDW
    0.37
    སྐ
    0.36
     susu
    0.36
    POSITIVE LOGITS
    ln
    0.46
     insuring
    0.46
    earing
    0.46
     множество
    0.46
    🍂
    0.45
     സാമൂഹ
    0.45
     grueling
    0.45
     ഓരോ
    0.43
    들에게
    0.41
    📋
    0.41
    Activations Density 0.002%

    No Known Activations