© 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. 41-GEMMASCOPE-2-RES-262K
    7. 61441
    Prev
    Next
    INDEX
    Explanations

    heavyweight fighter pirate theme war with Python

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sophisticated
    0.49
     ethereal
    0.49
     aguda
    0.49
     delikat
    0.48
     sofistic
    0.47
     elegante
    0.47
     aiguë
    0.46
    \<^
    0.46
     sophistication
    0.46
     delicate
    0.45
    POSITIVE LOGITS
     brute
    0.94
     behem
    0.86
     sturdy
    0.85
     Heavy
    0.80
     heavyweight
    0.79
    Strength
    0.78
     Strength
    0.77
     bulky
    0.77
    Heavy
    0.77
     bulldoz
    0.76
    Activations Density 0.008%

    No Known Activations