© 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. 86969
    Prev
    Next
    INDEX
    Explanations

    legislative and bill identifiers

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

    The neuron fires on numeric tokens—especially numbers with decimal points or other numerical 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
     \
    -1.70
     you
    -1.57
    ,"
    -1.55
     one
    -1.55
     według
    -1.53
    ’
    -1.52
     если
    -1.50
    when
    -1.48
    二日
    -1.38
     if
    -1.38
    POSITIVE LOGITS
     to
    2.11
     olika
    1.70
     finalement
    1.60
     that
    1.59
     différentes
    1.47
     gånger
    1.43
    iplin
    1.43
     realmente
    1.42
     verschillende
    1.41
     complètement
    1.41
    Activations Density 0.017%

    No Known Activations