© 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. 75287
    Prev
    Next
    INDEX
    Explanations

    amounts and quantities

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

    The neuron is activated by numerical tokens (e.g. counts, statistics, monetary or percentage values) 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
     it
    -1.47
    mathrm
    -1.23
     you
    -1.21
    ↵
    -1.20
    ↵↵
    -1.17
     your
    -1.14
     small
    -1.09
    同様に
    -1.07
     people
    -1.05
     their
    -1.05
    POSITIVE LOGITS
     about
    1.56
    Hanya
    1.52
    création
    1.48
     okolo
    1.42
    どうやら
    1.32
     around
    1.30
     ujar
    1.30
     salieron
    1.29
     between
    1.27
     İyi
    1.27
    Activations Density 0.063%

    No Known Activations