© 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. 10-GEMMASCOPE-RES-131K
    7. 87071
    Prev
    Next
    INDEX
    Explanations

    Centers for Disease Control

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

    organizational names or institutions, such as Centers for Disease Control, government agencies, and corporate entities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on numeric tokens—integers or decimal numbers—wherever they occur 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_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
     amea
    -1.65
     belge
    -1.64
     Nú
    -1.59
     jesu
    -1.57
     cerim
    -1.57
    Ꮀ
    -1.54
     cristo
    -1.53
     vélo
    -1.52
     haci
    -1.51
     camion
    -1.51
    POSITIVE LOGITS
     –
    1.70
     the
    1.69
     proporcionan
    1.51
     utilizadas
    1.45
     but
    1.42
     storici
    1.41
    senz
    1.40
    過來
    1.38
     jusqu
    1.38
     is
    1.36
    Activations Density 0.067%

    No Known Activations