© 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. 89887
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    煊
    0.43
    pocket
    0.42
    Youth
    0.40
    贄
    0.40
     टैबलेट
    0.40
    宅配
    0.40
     recetas
    0.39
    個人
    0.39
    abhut
    0.39
     кандай
    0.39
    POSITIVE LOGITS
     odd
    1.19
     Odd
    1.08
    Odd
    1.06
    odd
    0.96
    偶
    0.77
     alternating
    0.77
    奇
    0.70
     विषम
    0.68
     parity
    0.60
     unpaired
    0.59
    Activations Density 0.109%

    No Known Activations