© 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. 54657
    Prev
    Next
    INDEX
    Explanations

    inequality and disparities

    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
    APY
    0.38
     کمپیو
    0.36
    饨
    0.36
     св
    0.36
    ~.,
    0.36
     /\
    0.35
    క్షన్
    0.35
     희
    0.34
    ppsala
    0.34
     Тру
    0.34
    POSITIVE LOGITS
     inequalities
    0.65
     inequ
    0.65
     privileged
    0.65
     inequality
    0.64
     неравен
    0.64
     luxury
    0.64
     wealthy
    0.64
     Inequal
    0.61
     affluent
    0.61
     unequal
    0.59
    Activations Density 0.030%

    No Known Activations