© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    convolutional layers

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

    The neuron fires on floating‐point numeric tokens (numbers containing a decimal point).

    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
     cantidades
    0.95
    이랑
    0.95
    Ტ
    0.94
    ம்மா
    0.94
     mismas
    0.91
     posticis
    0.91
     fudai
    0.91
     kurie
    0.91
     অতঃ
    0.90
     mesmos
    0.89
    POSITIVE LOGITS
    ↵
    1.05
        
    0.91
     -
    0.90
     Northern
    0.88
     (
    0.86
     Case
    0.83
      
    0.83
     Corner
    0.83
     Ge
    0.82
    <eos>
    0.80
    Activations Density 0.000%

    No Known Activations