© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27485
    Prev
    Next
    INDEX
    Explanations

    divine punishment

    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
    Not in Any Lists

    No Comments

    Negative Logits
     মুগ্ধ
    0.45
     aspir
    0.42
     entusi
    0.42
     struts
    0.41
     estudante
    0.41
    感動
    0.40
    勇
    0.39
    Illegal
    0.39
    余裕
    0.39
     rêve
    0.39
    POSITIVE LOGITS
     punishment
    1.81
     punishments
    1.58
     Punishment
    1.48
     punish
    1.47
     punished
    1.35
     наказа
    1.35
     punishing
    1.32
     retribution
    1.22
     শাস্তি
    1.19
    惩
    1.18
    Activations Density 0.013%

    No Known Activations