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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41231
    Prev
    Next
    INDEX
    Explanations

    numerical statistics with yards

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

    The neuron peaks on standalone numeric tokens (i.e. numbers and statistical measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     then
    -1.57
     about
    -1.56
    équipements
    -1.50
     Tamaño
    -1.42
     meminta
    -1.42
     now
    -1.42
     nowy
    -1.37
     covering
    -1.36
     increasingly
    -1.35
     teraz
    -1.35
    POSITIVE LOGITS
    Who
    1.41
    Both
    1.38
     Кто
    1.34
    Usually
    1.33
    Для
    1.33
    when
    1.32
    噉
    1.27
    Would
    1.26
     فقط
    1.24
    Probably
    1.23
    Activations Density 0.024%

    No Known Activations