© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45668
    Prev
    Next
    INDEX
    Explanations

    at its core / at the heart

    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
    界的
    0.51
    рачи
    0.49
     විශේෂ
    0.46
     종료
    0.46
    종
    0.46
    上限
    0.45
     длину
    0.45
     сроки
    0.45
     kı
    0.44
     закін
    0.44
    POSITIVE LOGITS
     core
    0.88
    Core
    0.82
    core
    0.75
    的核心
    0.75
     Core
    0.69
    核心
    0.69
     핵심
    0.59
    kernel
    0.57
     essence
    0.56
    ↵
    0.54
    Activations Density 0.082%

    No Known Activations