© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4303
    Prev
    Next
    INDEX
    Explanations

    code block formatting or special characters

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

    This neuron detects numeric expressions (digits, measurements, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hi
    0.85
     llev
    0.76
    hi
    0.75
    trecht
    0.74
    こんばんは
    0.74
     astronaut
    0.73
     ganado
    0.73
    Ｚ
    0.71
     envi
    0.70
    ise
    0.68
    POSITIVE LOGITS
    NuGetPackage
    0.77
     nivå
    0.77
     ROUILLER
    0.77
    럼
    0.73
    ]},
    0.72
    aniyam
    0.71
    焘
    0.71
     바라
    0.70
    사이트
    0.69
     USART
    0.68
    Activations Density 0.001%

    No Known Activations