© 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. 10-GEMMASCOPE-RES-131K
    7. 13307
    Prev
    Next
    INDEX
    Explanations

    mathematical and code delimiters

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

    The main thing this neuron does is detect numeric values, especially decimal numbers, in the text or equations.

    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
    there
    -1.97
    xac
    -1.82
     {
    -1.78
    ቫ
    -1.75
    %;
    -1.75
     尔
    -1.72
    jącej
    -1.71
    ﻻ
    -1.69
    ellidos
    -1.68
     his
    -1.67
    POSITIVE LOGITS
    2
    2.53
    6
    2.28
    4
    2.25
    '
    2.17
    "
    2.05
    5
    2.00
    真的好
    1.98
    原本
    1.89
    Leírás
    1.85
    的很
    1.84
    Activations Density 0.000%

    No Known Activations