© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81822
    Prev
    Next
    INDEX
    Explanations

    Korean and religious concepts

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

    thesis

    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
    Negative Logits
    c
    0.58
     doesn
    0.52
    t
    0.48
     wouldn
    0.47
     ensure
    0.47
    FL
    0.46
     powinno
    0.46
    p
    0.45
    is
    0.45
     unfriendly
    0.45
    POSITIVE LOGITS
     하나님의
    0.54
     అతని
    0.52
    पीरियंस
    0.49
     하나님
    0.48
     삶
    0.47
    薷
    0.46
     말미암아
    0.45
     자신의
    0.45
     그의
    0.45
     teammate
    0.45
    Activations Density 0.001%

    No Known Activations