© 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. 56582
    Prev
    Next
    INDEX
    Explanations

    enzymes and proteases

    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
     additive
    0.39
    additive
    0.39
    Volt
    0.38
     uridine
    0.37
    🗸
    0.37
     জুড়ে
    0.37
    ਣੀ
    0.36
    Additive
    0.36
    频道
    0.36
    "=>
    0.36
    POSITIVE LOGITS
     proteolytic
    0.98
     protease
    0.97
     prote
    0.78
    prote
    0.75
     Prote
    0.68
     MMP
    0.68
     metall
    0.67
     enzymes
    0.58
    metall
    0.55
     destructor
    0.52
    Activations Density 0.006%

    No Known Activations