© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49274
    Prev
    Next
    INDEX
    Explanations

    punish and punishment concepts

    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_16_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
    Start
    0.78
     s
    0.74
     r
    0.73
    ↵
    0.70
     à
    0.69
    CC
    0.67
     w
    0.66
     i
    0.66
     ve
    0.65
    That
    0.65
    POSITIVE LOGITS
     punishment
    1.21
     punish
    1.12
     punished
    1.02
     penal
    0.96
     punishing
    0.91
     punitive
    0.85
     Punishment
    0.85
     punishments
    0.84
    懲
    0.80
     наказа
    0.80
    Activations Density 0.022%

    No Known Activations