© 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. 65130
    Prev
    Next
    INDEX
    Explanations

    numbers associated with specific items

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

    The neuron activates on numeric quantity information—tokens representing measurements, counts, or amounts (numbers and their associated unit or descriptor).

    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
     to
    -1.45
    臜
    -1.44
     rapor
    -1.24
    𖤣
    -1.23
     整理
    -1.21
     inspiração
    -1.20
     it
    -1.20
     mostrarán
    -1.20
     pieni
    -1.18
     constituye
    -1.18
    POSITIVE LOGITS
     którzy
    1.52
     azonban
    1.45
    Сюжет
    1.42
    .'
    1.37
    あなたは
    1.36
    Ở
    1.36
    ността
    1.34
     adduced
    1.34
     '
    1.32
     reeling
    1.32
    Activations Density 0.012%

    No Known Activations