© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119615
    Prev
    Next
    INDEX
    Explanations

    numbers and specific codes

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

    The neuron fires whenever it sees a standalone numeric token (i.e. digits making up 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_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
     for
    -2.09
     was
    -1.61
     are
    -1.59
     has
    -1.44
     on
    -1.41
     Это
    -1.38
     if
    -1.38
     He
    -1.38
     in
    -1.37
     would
    -1.34
    POSITIVE LOGITS
    躥
    1.58
    你有
    1.56
    خیلی
    1.52
    縢
    1.50
    Actually
    1.50
    VERY
    1.49
    夲
    1.48
    苙
    1.48
     vosotros
    1.45
     смогли
    1.45
    Activations Density 0.011%

    No Known Activations