© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5246
    Prev
    Next
    INDEX
    Explanations

    Ordering instance

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

    The neuron fires on strings of digits (including long numbers, decimals, and numeric identifiers).

    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
    mensaje
    1.00
    DESIGN
    0.80
    ержа
    0.78
     женщины
    0.77
    sandwich
    0.76
    𝚖
    0.75
    compress
    0.75
    ??
    0.75
    GLISH
    0.74
    얇
    0.73
    POSITIVE LOGITS
    笂
    0.73
     Graphs
    0.70
    زمة
    0.69
     ราย
    0.66
    <0xF3>
    0.65
     million
    0.65
    庐
    0.64
     Properties
    0.64
     Overview
    0.64
     बजे
    0.63
    Activations Density 0.001%

    No Known Activations