© 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. 66769
    Prev
    Next
    INDEX
    Explanations

    sequencing of numbers or items

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

    The neuron activates on numeric tokens—especially numbers with decimal points—i.e. it detects numeric 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
     COMPARISON
    -1.00
    nende
    -0.92
    こんに
    -0.91
     planètes
    -0.90
    télé
    -0.87
    odore
    -0.86
    香味
    -0.86
     numéros
    -0.85
     població
    -0.85
    сей
    -0.85
    POSITIVE LOGITS
     Judaism
    1.03
     to
    0.99
    Syn
    0.92
    第二个
    0.91
     and
    0.88
    syn
    0.82
    aka
    0.81
     Co
    0.79
    ведения
    0.78
    謾
    0.78
    Activations Density 0.051%

    No Known Activations