© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11682
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is spot numeric expressions and measurement values (e.g. numbers, percentages, units, dates).

    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_31_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
     keseluruhan
    0.85
    개월
    0.80
    珀
    0.79
     ಏನು
    0.77
    
    0.77
     erkek
    0.77
     อะไร
    0.76
    ewnętr
    0.76
     extracción
    0.76
     chắc
    0.76
    POSITIVE LOGITS
     prompt
    0.71
     (
    0.69
     “
    0.69
     বিনিম
    0.68
     \"
    0.67
     Prompt
    0.66
    TM
    0.65
     tast
    0.64
    ‖
    0.62
    LIN
    0.62
    Activations Density 0.000%

    No Known Activations