© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7640
    Prev
    Next
    INDEX
    Explanations

    declaratory judgment

    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_39_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
     criminal
    0.52
     Criminal
    0.50
    Criminal
    0.49
     punishable
    0.49
     punish
    0.48
     уголов
    0.48
     offences
    0.48
    罪
    0.47
    criminal
    0.46
    Prosecutors
    0.46
    POSITIVE LOGITS
     declaratory
    0.81
    Declar
    0.61
     civil
    0.60
     Civil
    0.60
    declar
    0.60
     Declar
    0.58
     declar
    0.56
    Civil
    0.55
     सिविल
    0.53
     CIVIL
    0.53
    Activations Density 0.038%

    No Known Activations