© 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. 35953
    Prev
    Next
    INDEX
    Explanations

    quantities of items

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

    The neuron fires on numeric tokens—digits or numbers (including integers, decimals, and counts) 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
    NonQuery
    -0.86
    tilhar
    -0.85
    mény
    -0.83
     then
    -0.81
    〕
    -0.80
     Berufs
    -0.79
     න
    -0.78
     that
    -0.78
    ALLED
    -0.77
     основе
    -0.76
    POSITIVE LOGITS
     thousands
    1.41
     numerous
    1.26
    thousands
    1.23
     countless
    1.21
     hundreds
    1.19
    hundreds
    1.15
     many
    1.09
     myriad
    1.09
     milliers
    1.05
     centaines
    1.03
    Activations Density 0.064%

    No Known Activations