© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38721
    Prev
    Next
    INDEX
    Explanations

    numbers, series, or sequences

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

    The neuron specializes in spotting numeric tokens and their related punctuation (digits, commas, decimal points) 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
    ̴
    -1.13
    saat
    -1.01
     guitare
    -1.00
    有一定的
    -0.99
    şak
    -0.98
    ícola
    -0.97
    Supplemental
    -0.95
    Inggris
    -0.95
     étoient
    -0.94
    wness
    -0.94
    POSITIVE LOGITS
     any
    1.27
     this
    1.16
    ar
    1.04
     voedsel
    0.96
    al
    0.94
     everything
    0.93
     it
    0.90
    R
    0.86
     one
    0.86
     pulley
    0.85
    Activations Density 0.076%

    No Known Activations