© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on numeric tokens and numerical expressions (e.g. years, percentages, measurements).

    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
    Whilst
    1.00
    Firstly
    0.98
     Whilst
    0.92
    ()/
    0.92
    にて
    0.91
     THIS
    0.91
    Sadly
    0.91
    This
    0.89
    /
    0.89
    等の
    0.85
    POSITIVE LOGITS
     spokeswoman
    0.91
     prosecutors
    0.85
     aides
    0.80
     dozens
    0.76
     backers
    0.74
     비슷한
    0.73
     officials
    0.73
     lawmakers
    0.72
     filings
    0.72
     congressional
    0.71
    Activations Density 0.307%

    No Known Activations