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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118866
    Prev
    Next
    INDEX
    Explanations

    serum and plasma proteins

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

    This neuron identifies biochemical proteins and compounds mentioned in scientific papers, particularly focusing on proteins like albumin, globulin, and various glycoproteins.

    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
    бър
    -0.81
    🦖
    -0.80
    GSM
    -0.79
    basename
    -0.76
    诛
    -0.73
    waan
    -0.73
    atiles
    -0.71
    ujeme
    -0.71
     sensibility
    -0.71
    uron
    -0.70
    POSITIVE LOGITS
     albumin
    2.00
     serum
    1.81
     Album
    1.79
     plasma
    1.65
     album
    1.61
     Serum
    1.57
    Album
    1.55
    album
    1.48
    serum
    1.40
     Plasma
    1.34
    Activations Density 0.163%

    No Known Activations