© 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. 22-GEMMASCOPE-RES-131K
    7. 9295
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    The neuron activates on numeric expressions (quantities, counts, and statistics) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     that
    -1.48
     neón
    -1.13
    ܞ
    -1.07
    udahan
    -1.05
    ieważ
    -1.02
    astă
    -1.01
     který
    -0.99
     навіть
    -0.99
     which
    -0.97
    hiana
    -0.97
    POSITIVE LOGITS
     whereas
    2.83
     while
    2.47
     tandis
    2.41
     mentre
    2.06
     mientras
    1.84
     followed
    1.76
     जबकि
    1.64
     ส่วน
    1.63
    while
    1.60
     natomiast
    1.56
    Activations Density 0.059%

    No Known Activations