© 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. 35883
    Prev
    Next
    INDEX
    Explanations

    HTMLNode, date, election information

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

    The neuron is specialized to pick out numeric tokens (especially multi-digit and decimal numbers) 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
    Público
    -0.82
     затра
    -0.80
    tać
    -0.79
    enseits
    -0.78
    只是一
    -0.78
    Răsp
    -0.78
    wige
    -0.77
    rigos
    -0.77
     hierdie
    -0.77
     inútil
    -0.77
    POSITIVE LOGITS
     Privacidad
    1.04
     pageContext
    1.02
    💁
    0.98
    넨
    0.98
     卧室
    0.94
    ções
    0.92
     Zwecke
    0.91
    🧘
    0.91
    烃
    0.91
    ROOMS
    0.91
    Activations Density 0.008%

    No Known Activations