© 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. 130586
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numerical tokens—any figures or measurements (e.g. “362,” “109.5,” “143,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    situated, reduced size, including high

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     then
    -1.30
    @[+][
    -1.08
     anderer
    -1.03
    \|_{
    -1.02
    mathcal
    -1.01
    éal
    -1.01
     other
    -0.98
    ensatz
    -0.95
     otras
    -0.95
    izational
    -0.94
    POSITIVE LOGITS
    竟然是
    1.20
    Neither
    0.98
     neither
    0.96
    preparing
    0.93
     logiciels
    0.90
    Essentially
    0.90
    neither
    0.89
    rugu
    0.88
     devrez
    0.87
     sprinkles
    0.85
    Activations Density 0.103%

    No Known Activations