© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6847
    Prev
    Next
    INDEX
    Explanations

    opponent / adversary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     leadership
    0.60
    导
    0.55
    倡
    0.55
     guiding
    0.55
    权利
    0.55
    iduciary
    0.54
     forwarding
    0.54
    ifton
    0.53
    導
    0.53
    rieve
    0.53
    POSITIVE LOGITS
     opponent
    1.84
     opponents
    1.78
    对手
    1.66
    opponent
    1.66
     против
    1.56
     Gegner
    1.52
     adversary
    1.47
     protiv
    1.39
     melawan
    1.39
     adversaries
    1.38
    Activations Density 0.300%

    No Known Activations