© 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. 73604
    Prev
    Next
    INDEX
    Explanations

    describing diverse contexts and quantities

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

    The neuron fires on words that convey multiplicity or variety—terms signaling diverse, multiple, or varied elements.

    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
     to
    -1.25
     which
    -1.10
     before
    -1.09
     would
    -1.04
     helps
    -0.98
     because
    -0.98
     attempt
    -0.97
     those
    -0.96
     help
    -0.95
     after
    -0.94
    POSITIVE LOGITS
     zonder
    1.22
     tanpa
    1.18
     कई
    1.16
     ohne
    1.16
     parfois
    1.14
     csomag
    1.07
     nehé
    1.06
     soms
    1.05
     verschillende
    1.03
     több
    1.03
    Activations Density 0.068%

    No Known Activations