© 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. 119295
    Prev
    Next
    INDEX
    Explanations

    inhibitory and regulatory molecules

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

    proteins and molecules involved in immune system responses, inflammation, and cellular signaling 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
     asparagus
    -0.81
     terrier
    -0.77
     Cyclone
    -0.75
     tulip
    -0.74
     tufted
    -0.73
     draper
    -0.73
     Inferior
    -0.72
    itans
    -0.70
     Altar
    -0.70
     torches
    -0.70
    POSITIVE LOGITS
     inhibitory
    1.80
     anti
    1.52
     protective
    1.40
     inhibit
    1.30
     damp
    1.29
     regulatory
    1.28
     inhibitor
    1.25
    protective
    1.23
     inhibition
    1.21
     inhibits
    1.18
    Activations Density 0.371%

    No Known Activations