© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75042
    Prev
    Next
    INDEX
    Explanations

    XML tags and code constructs

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

    This neuron activates on numeric literals (digits or numbers) 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_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
     Brussels
    -1.13
    ́
    -1.11
     Singapore
    -1.10
    ì
    -1.04
     then
    -1.03
     Tokyo
    -1.01
     Moscow
    -1.00
    dracht
    -1.00
     massage
    -0.99
     TikTok
    -0.99
    POSITIVE LOGITS
    も行
    1.34
     difficoltà
    1.23
    OREM
    1.16
    を行い
    1.16
    えっ
    1.15
    隄
    1.15
    Hersteller
    1.12
     esplor
    1.10
    ابان
    1.07
    ترن
    1.05
    Activations Density 0.001%

    No Known Activations