© 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. 34-GEMMASCOPE-RES-131K
    7. 84411
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

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

    The neuron responds to multi‐digit numeric tokens, especially large numbers such as publication years or volume/page identifiers in academic citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Godt
    -0.90
     Baños
    -0.89
     Adresse
    -0.88
     Grafik
    -0.87
     Politik
    -0.87
    重建
    -0.83
    віч
    -0.83
    temperatur
    -0.83
    ᴥ
    -0.82
     разные
    -0.81
    POSITIVE LOGITS
    وائد
    0.91
     zelfs
    0.90
     nawet
    0.84
     while
    0.84
    neider
    0.82
     next
    0.78
    fia
    0.77
    automne
    0.76
    rops
    0.72
     between
    0.72
    Activations Density 0.006%

    No Known Activations