© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21424
    Prev
    Next
    INDEX
    Explanations

    prove innocence

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ACCESS
    0.45
     ইউনিভার
    0.45
    式
    0.45
    繁忙時間服務
    0.44
     changeable
    0.44
    鹵
    0.44
    рко
    0.43
     peningkatan
    0.43
    鐮
    0.42
     布
    0.41
    POSITIVE LOGITS
     innocence
    1.73
     innocent
    1.70
     exoner
    1.59
     innoc
    1.43
     Innocent
    1.34
     Innoc
    1.28
     inoc
    1.08
     defend
    1.06
     defended
    1.06
     acquitted
    1.03
    Activations Density 0.001%

    No Known Activations