© 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-262K
    7. 24848
    Prev
    Next
    INDEX
    Explanations

    pleading guilty and plea bargains

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mamma
    0.40
    aporte
    0.40
    ༔
    0.40
    蓍
    0.38
    理論
    0.38
    Theoretical
    0.38
     tatu
    0.38
     revision
    0.37
    媛
    0.37
    鍾
    0.37
    POSITIVE LOGITS
     pleaded
    1.57
     plead
    1.54
     plea
    1.48
     pleads
    1.48
     pled
    1.35
     pleading
    1.32
     Plea
    1.32
     pleas
    1.23
     guilty
    0.99
     пле
    0.97
    Activations Density 0.003%

    No Known Activations