© 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. 5883
    Prev
    Next
    INDEX
    Explanations

    street types and abbreviations

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

    The neuron activates on floating‐point numeric tokens (decimal numbers).

    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
     অনেকগুলি
    0.70
    
    0.63
     Knoten
    0.63
     географи
    0.61
     añadi
    0.61
     заместитель
    0.58
     Uniwers
    0.58
     ২৭
    0.57
     számos
    0.57
     EventEmitter
    0.57
    POSITIVE LOGITS
    New
    0.75
    Pune
    0.70
    .
    0.64
    Rew
    0.63
    Popup
    0.63
    Dubai
    0.63
    Popul
    0.62
    Susan
    0.61
    Shanghai
    0.61
    Baltimore
    0.61
    Activations Density 0.016%

    No Known Activations