© 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. 10-GEMMASCOPE-RES-131K
    7. 99670
    Prev
    Next
    INDEX
    Explanations

    metabolites produced by microbes

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

    The neuron identifies scientific terms related to metabolites and microorganisms, particularly in biological and pharmaceutical contexts.

    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
    al
    -2.86
    T
    -2.66
    —"
    -2.47
    m
    -2.47
     —
    -2.34
    遄
    -2.34
    h
    -2.33
    在我
    -2.33
    孓
    -2.33
    —
    -2.31
    POSITIVE LOGITS
    
    2.89
    놋
    2.59
    a
    2.59
    那种
    2.55
    𐌽
    2.50
     Preguntas
    2.48
    他
    2.48
     جيدة
    2.45
    塤
    2.44
     namun
    2.38
    Activations Density 0.031%

    No Known Activations