© 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. 10-GEMMASCOPE-RES-131K
    7. 105875
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structure

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

    The neuron is detecting numeric tokens (numbers, including integers and decimals) 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
    -
    -1.88
     one
    -1.70
     we
    -1.62
     two
    -1.56
     they
    -1.49
     I
    -1.47
     because
    -1.46
    ,
    -1.38
     from
    -1.34
     until
    -1.34
    POSITIVE LOGITS
    夘
    1.73
     )}
    1.51
    桫
    1.49
    抟
    1.48
    굼
    1.46
    ensiva
    1.45
    inafter
    1.43
     bepa
    1.41
     SolutionA
    1.41
    jorde
    1.41
    Activations Density 0.083%

    No Known Activations