© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7847
    Prev
    Next
    INDEX
    Explanations

    Nij, Tuj, Vaj, Buj, nj

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     değiş
    0.40
    Changing
    0.40
     zmienia
    0.39
     change
    0.39
     Changing
    0.38
     changing
    0.38
    Adapt
    0.38
     changed
    0.38
    {
    0.38
    🈯
    0.36
    POSITIVE LOGITS
    ्ज
    0.51
    Ⲓ
    0.46
    ารย์
    0.43
    تمع
    0.42
    ﻑ
    0.41
     craindre
    0.41
    ίας
    0.41
    味料
    0.41
    ्ञ
    0.40
    ன்று
    0.40
    Activations Density 0.103%

    No Known Activations