© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74318
    Prev
    Next
    INDEX
    Explanations

    enzyme names ending in ase

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

    enzyme names and their chemical functions in biochemical literature.

    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_10/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
    LLING
    -1.58
     särsk
    -1.39
     réfugiés
    -1.36
     készült
    -1.30
    ,»
    -1.30
     добавил
    -1.30
    \",\"
    -1.28
    ,\\
    -1.27
    cellent
    -1.27
    ↵↵
    -1.27
    POSITIVE LOGITS
    The
    1.57
    もありますが
    1.44
    镚
    1.41
    節目
    1.40
                    
    1.38
     },
    1.33
    ])
    1.32
     Like
    1.28
     aseg
    1.28
    鯢
    1.27
    Activations Density 0.221%

    No Known Activations