© 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. 58762
    Prev
    Next
    INDEX
    Explanations

    numbers after slashes

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

    The neuron activates on numeric tokens (digit sequences) in the text, such as years or other numbers.

    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
     four
    -1.28
     six
    -1.26
     eight
    -1.21
     three
    -1.18
     large
    -1.17
     sophisticated
    -1.16
     prominent
    -1.15
     five
    -1.15
     it
    -1.12
     ostensibly
    -1.09
    POSITIVE LOGITS
     ২০১
    1.80
     २०
    1.71
     vuonna
    1.51
     YYYY
    1.49
     năm
    1.37
     ۲۰۱
    1.34
     undated
    1.27
    YYYY
    1.27
     ২০
    1.27
     בשנת
    1.26
    Activations Density 0.068%

    No Known Activations