© 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. 103690
    Prev
    Next
    INDEX
    Explanations

    protein domain and region

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

    structural domains in proteins, particularly those related to molecular biology terminology like zinc fingers, domains, and terminal regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on tokens containing digits (e.g. numeric values, gene or domain identifiers, and hyphenated number sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    kelijkheid
    -0.83
    /{
    -0.77
     MEMBER
    -0.75
    ტი
    -0.74
     Enkel
    -0.73
     TOPIC
    -0.71
     Fakta
    -0.70
     komis
    -0.69
     CONTRIBUTOR
    -0.68
     membro
    -0.67
    POSITIVE LOGITS
     domain
    2.19
     domains
    2.17
     Domains
    1.88
     Domain
    1.80
    Domain
    1.73
    domains
    1.70
    domain
    1.66
    Domains
    1.52
    DOMAIN
    1.45
     region
    1.44
    Activations Density 0.203%

    No Known Activations