© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10779
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily picks out numeric expressions (dates, quantities, measurements, etc.).

    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
    about
    0.66
     horrid
    0.64
     ignorant
    0.63
     respectable
    0.61
    Mr
    0.61
    "
    0.59
    ji
    0.59
    --
    0.57
    Ji
    0.57
    ába
    0.57
    POSITIVE LOGITS
     heartwarming
    0.84
     идеально
    0.79
     nutzen
    0.77
     รวมถึง
    0.76
     transitioned
    0.76
     مرتبط
    0.75
     geospatial
    0.75
     transitioning
    0.74
     unassuming
    0.74
     comprobar
    0.73
    Activations Density 0.047%

    No Known Activations