© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48722
    Prev
    Next
    INDEX
    Explanations

    accusing opponents of subversion

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Theoretically
    0.48
    一些
    0.43
     நிகழ்
    0.43
     réalise
    0.42
    期待
    0.42
    Autonomous
    0.41
    Methylsulfanyl
    0.41
     Ereign
    0.41
    кров
    0.40
    羡
    0.40
    POSITIVE LOGITS
     enemy
    0.61
     enemies
    0.57
    敌人
    0.56
     traitor
    0.56
     communist
    0.55
    敵人
    0.55
     terrorist
    0.54
     caricature
    0.54
     menacing
    0.52
     accusing
    0.52
    Activations Density 0.054%

    No Known Activations