© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2683
    Prev
    Next
    INDEX
    Explanations

    Japanese suffix-like particles

    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_16_width_65k_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
    '
    0.97
    ↵↵
    0.84
    ra
    0.74
    ﻮ
    0.74
     exposé
    0.68
     (
    0.67
     Yankees
    0.67
    𝐖
    0.64
     рассматри
    0.64
     ofic
    0.64
    POSITIVE LOGITS
     in
    1.28
    ين
    1.10
    도
    1.07
    ق
    1.06
    ও
    1.05
     في
    1.02
    在
    0.96
    માં
    0.93
    も
    0.93
    ى
    0.93
    Activations Density 0.124%

    No Known Activations