© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3553
    Prev
    Next
    INDEX
    Explanations

    religious organizations or middle east

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

    category followed by descriptor

    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_53_width_65k_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
     بالټ
    0.45
    ⓪
    0.41
    ｆ
    0.40
    ________
    0.38
    队友
    0.37
    র্ত
    0.35
    变量
    0.35
     Englishman
    0.35
     congressman
    0.35
    therners
    0.35
    POSITIVE LOGITS
    как
    0.43
     তৈরী
    0.39
     propria
    0.38
     umum
    0.38
    விய
    0.36
     ГӀ
    0.36
     nedir
    0.35
     ["[
    0.35
     знако
    0.35
     miglia
    0.34
    Activations Density 0.081%

    No Known Activations