© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or operators

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

    This neuron activates on numerical tokens (digits or numeric literals) such as numbers in equations, measurements (px), or hex color codes.

    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
     любого
    -1.03
     всеми
    -0.93
     RECOMMEND
    -0.90
     any
    -0.90
     qualquer
    -0.89
     luminoso
    -0.88
     utafitiHapana
    -0.88
     mọi
    -0.87
     cualquier
    -0.86
     любой
    -0.86
    POSITIVE LOGITS
     darunter
    0.95
    ən
    0.85
    맙
    0.85
     precedenti
    0.84
     not
    0.84
    ndose
    0.83
    Not
    0.82
    engager
    0.80
    —”
    0.79
    法的
    0.79
    Activations Density 0.219%

    No Known Activations