© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    10 unique

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

    The neuron strongly activates on numeric digit tokens (especially parts of multi‐digit 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
    РА
    0.78
    Ве
    0.78
    的那
    0.73
     demean
    0.73
                 
    0.70
                  
    0.67
    DEBUG
    0.66
    л
    0.66
                
    0.66
    ра
    0.66
    POSITIVE LOGITS
     тысяч
    1.08
     dozen
    0.99
     lenders
    0.96
     különböző
    0.96
     শতাধিক
    0.96
     thousand
    0.94
     ribu
    0.93
    0
    0.89
    thousand
    0.88
    数百
    0.88
    Activations Density 0.511%

    No Known Activations