© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129283
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric measurement tokens (e.g. numbers and decimal values) in the document.

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

    administration or stress

    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
     such
    -0.89
    ọi
    -0.88
    重要
    -0.86
    payer
    -0.82
     clothes
    -0.81
    해서
    -0.80
     and
    -0.80
    kug
    -0.79
     when
    -0.79
     comments
    -0.78
    POSITIVE LOGITS
    endaftar
    1.06
    ppuden
    0.89
     tận
    0.85
    ядок
    0.85
    roxene
    0.83
    ഒ
    0.82
     dejado
    0.82
    TION
    0.80
    むしろ
    0.80
    但这
    0.80
    Activations Density 0.030%

    No Known Activations