© 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. 34-GEMMASCOPE-RES-131K
    4. 90353
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and multilingual terms

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

    The neuron fires on numeric literals (especially multi‐digit or signed numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    的笑容
    -0.97
    os
    -0.93
     حتی
    -0.90
    的心情
    -0.88
     sufren
    -0.88
     любы
    -0.88
     (
    -0.88
    的模样
    -0.88
     veckan
    -0.86
     trasero
    -0.85
    POSITIVE LOGITS
    gruß
    1.12
     diskusi
    1.09
    Cuándo
    1.09
    =”
    1.08
     Itália
    1.05
     sulit
    1.03
    pierw
    1.02
    Cuidado
    1.02
     nela
    1.02
    Fácil
    1.01
    Activations Density 0.006%

    No Known Activations