© 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. 135184
    Prev
    Next
    INDEX
    Explanations

    skilled thief, goddess, supreme, AI agents

    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
     spies
    0.47
     никто
    0.46
     niemand
    0.46
    ش
    0.45
     schwarz
    0.45
    專輯
    0.44
    ни
    0.44
    νη
    0.44
     kein
    0.44
     immort
    0.43
    POSITIVE LOGITS
    Fu
    0.43
    eniya
    0.43
    Gp
    0.43
    Deb
    0.42
    $=\
    0.41
     protrusion
    0.41
     निर्मित
    0.41
    MDEwOlJlcG
    0.41
     Zhejiang
    0.41
     করিয়াছিল
    0.40
    Activations Density 0.003%

    No Known Activations