© 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. 60726
    Prev
    Next
    INDEX
    Explanations

    greater/less than comparisons

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

    The neuron strongly activates on comparative phrases involving “greater than” or “less than,” especially around numeric or operator contexts.

    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
    暮
    -0.76
     Cassidy
    -0.75
    -)
    -0.75
    Joyce
    -0.74
     gått
    -0.70
    rium
    -0.69
     Trieste
    -0.69
    şekkür
    -0.69
    fez
    -0.69
    Citizens
    -0.67
    POSITIVE LOGITS
     than
    1.21
     Than
    0.93
    than
    0.91
    Than
    0.88
    THAN
    0.82
     Relocation
    0.72
    Postup
    0.69
    $<$
    0.68
     señala
    0.68
     scheint
    0.67
    Activations Density 0.071%

    No Known Activations