© 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. 72908
    Prev
    Next
    INDEX
    Explanations

    dimensions and multiplication

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

    The neuron detects numerical dimension expressions (numbers separated by “x”) indicating size 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
    is
    -1.98
    {
    -1.55
    ai
    -1.51
    an
    -1.50
    ii
    -1.48
    -1.45
    _
    -1.45
     \
    -1.45
     &
    -1.43
    ----------------
    -1.43
    POSITIVE LOGITS
     occhiali
    1.57
     articoli
    1.52
    媃
    1.51
     蜜
    1.48
    danke
    1.46
    Dimanche
    1.45
     diduga
    1.42
    Directeur
    1.41
    coffret
    1.41
     estándares
    1.41
    Activations Density 0.023%

    No Known Activations