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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60843
    Prev
    Next
    INDEX
    Explanations

    ubiquitin and protein degradation

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

    references to ubiquitin ligases, particularly E3 ligases, and protein degradation pathways.

    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
     DSC
    -0.81
    madores
    -0.79
    baijan
    -0.79
    CURY
    -0.76
    hloromethane
    -0.75
    UnifiedTopology
    -0.74
    蛛
    -0.74
    股份
    -0.74
    UMENT
    -0.74
     voting
    -0.73
    POSITIVE LOGITS
     ubiquit
    1.87
     degradation
    1.40
     Ubi
    1.38
    Ubi
    1.22
    ubi
    1.16
     Degradation
    1.16
     ubi
    1.13
     degrade
    1.13
     Ub
    1.09
    Ub
    1.02
    Activations Density 0.114%

    No Known Activations