© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104244
    Prev
    Next
    INDEX
    Explanations

    dollar amounts, percentages, and quantities

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

    The neuron activates primarily on numeric tokens—figures, percentages, dollar amounts, and other standalone numbers.

    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
     their
    -1.45
     with
    -1.44
     relating
    -1.41
     most
    -1.40
    —
    -1.22
     designated
    -1.21
    为何
    -1.19
     vital
    -1.19
     as
    -1.18
    er
    -1.17
    POSITIVE LOGITS
     parfü
    1.64
     kutu
    1.63
     cinquante
    1.62
    ໊
    1.61
     galeri
    1.61
     diki
    1.60
     boneka
    1.60
     Décembre
    1.58
     göm
    1.58
     tulis
    1.58
    Activations Density 0.069%

    No Known Activations