© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8773
    Prev
    Next
    INDEX
    Explanations

    everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    这两
    0.77
    这两个
    0.73
    兌
    0.71
    ޘ
    0.71
     ယ
    0.70
     altre
    0.70
    près
    0.69
     እነዚህ
    0.68
     parallelogram
    0.67
    )=$
    0.67
    POSITIVE LOGITS
     everyone
    4.36
     Everyone
    3.98
    Everyone
    3.93
     everybody
    3.91
    everyone
    3.81
    Everybody
    3.48
     Everybody
    3.47
     iedereen
    3.11
     الجميع
    2.92
    ทุกคน
    2.81
    Activations Density 0.111%

    No Known Activations