© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109688
    Prev
    Next
    INDEX
    Explanations

    Masonic, lodge, fellowship, temple, mysteries

    np_acts-logits-general · gemini-2.5-flash-lite

    secret societies, esoteric orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    飛ば
    0.46
    biotic
    0.46
    ॉप्टर
    0.45
    フォル
    0.44
     ダイ
    0.44
     технологі
    0.43
    爽
    0.43
     کاربر
    0.43
     lógico
    0.42
    ◎
    0.42
    POSITIVE LOGITS
     Masonic
    0.97
     Fraternity
    0.86
     Freem
    0.73
     fraternity
    0.68
     brotherhood
    0.66
     fraternal
    0.65
     Membership
    0.65
     Ritual
    0.64
    Membership
    0.63
     membership
    0.61
    Activations Density 0.063%

    No Known Activations