© 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. 59065
    Prev
    Next
    INDEX
    Explanations

    nitrogen fixation

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

    scientific content related to nitrogen fixation, particularly in biological contexts.

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

    The neuron is strongly triggered by technical biological terms describing heterocyst differentiation and dinitrogen (nitrogen) fixation processes.

    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
     Dave
    -0.77
    Dave
    -0.77
    linien
    -0.76
     useAppContext
    -0.75
    retung
    -0.73
    Modifier
    -0.73
    glyphicon
    -0.71
    unya
    -0.70
    yeon
    -0.69
     Übergang
    -0.69
    POSITIVE LOGITS
     nitrogen
    2.30
    nitrogen
    1.90
     Nitrogen
    1.74
    Nitrogen
    1.69
     fixation
    1.52
     fix
    1.36
     Fixation
    1.34
    fix
    1.33
     fixing
    1.25
     FIX
    1.23
    Activations Density 0.026%

    No Known Activations