© 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. 22-GEMMASCOPE-RES-131K
    7. 70588
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets

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

    The neuron strongly activates on any token containing numbers (digit sequences).

    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
    随意
    -1.13
     will
    -1.08
     пород
    -1.05
    It
    -1.04
    ējās
    -1.02
    ⾃
    -1.02
    acionais
    -0.97
    шем
    -0.96
    桎
    -0.96
     Новости
    -0.95
    POSITIVE LOGITS
    ittäin
    1.25
     estrelas
    1.10
    Referințe
    1.08
     recaudación
    1.06
    Tidak
    1.05
     otros
    1.05
     府
    1.04
    Kelas
    1.04
    (()=>{
    1.03
     sáb
    1.03
    Activations Density 0.006%

    No Known Activations