© 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. 13106
    Prev
    Next
    INDEX
    Explanations

    simultaneously or together

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

    The neuron responds to any numeric substrings (digits or multi-digit numbers) embedded in tokens.

    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
    तीय
    -0.90
    に行って
    -0.82
     Tickets
    -0.82
     informée
    -0.79
     jusqu
    -0.77
     your
    -0.77
     yardım
    -0.76
     įsi
    -0.74
    Tickets
    -0.73
    akterysty
    -0.73
    POSITIVE LOGITS
     одновременно
    1.20
     zugleich
    1.17
     simultaneously
    1.17
    simult
    0.98
    Պ
    0.96
    ంది
    0.95
     μαζί
    0.94
     together
    0.92
     senate
    0.91
     insieme
    0.91
    Activations Density 0.034%

    No Known Activations