© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43179
    Prev
    Next
    INDEX
    Explanations

    church, club, station

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

    The neuron activates on numeric expressions—particularly decimal numbers and other quantities (e.g. prices, measurements, years).

    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
     or
    -1.43
     (
    -1.33
    模样
    -1.30
    悲しい
    -1.27
     utilizan
    -1.22
    cticas
    -1.22
     -
    -1.21
    менения
    -1.19
     StringField
    -1.17
     летом
    -1.16
    POSITIVE LOGITS
     now
    1.61
     still
    1.52
     already
    1.45
    :……
    1.44
     always
    1.43
    ⽼
    1.41
    前言
    1.39
    Zeneca
    1.36
     geforce
    1.35
     églises
    1.34
    Activations Density 0.006%

    No Known Activations