© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30274
    Prev
    Next
    INDEX
    Explanations

    MMPs and proteases

    np_acts-logits-general · gemini-2.5-flash-lite

    protein-related enzyme terminology, particularly words like "protease," "metalloproteinase," and enzyme names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aram
    -0.77
     Cranston
    -0.75
     enää
    -0.72
    υγ
    -0.72
     Malang
    -0.71
     beats
    -0.71
    غم
    -0.71
     licorne
    -0.69
     والد
    -0.69
     braids
    -0.69
    POSITIVE LOGITS
     protease
    1.31
     cleavage
    1.07
     MMP
    1.05
     zy
    0.99
     pep
    0.97
    MMP
    0.96
     ADAM
    0.93
     prote
    0.90
     cle
    0.90
     gelatin
    0.89
    Activations Density 0.167%

    No Known Activations