© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81350
    Prev
    Next
    INDEX
    Explanations

    Russian 'р' and 'Ра'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     जड़ों
    0.38
     chiff
    0.38
    俆
    0.37
     далее
    0.35
     গিয়াছেন
    0.35
    記録
    0.35
    根
    0.35
     useRef
    0.35
     Guaranteed
    0.35
     রয়ে
    0.35
    POSITIVE LOGITS
     grows
    0.42
     tumbuh
    0.37
     groei
    0.36
     explores
    0.36
     siang
    0.35
    grow
    0.35
     wards
    0.35
    пах
    0.35
    🦂
    0.35
    playing
    0.34
    Activations Density 0.000%

    No Known Activations