© 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. 236
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly activated by numeric expressions (numbers and figures).

    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
    ↵↵
    0.43
    ()
    0.42
     (
    0.41
     in
    0.41
    y
    0.41
     ()
    0.39
    2
    0.39
     from
    0.39
    1
    0.38
     or
    0.37
    POSITIVE LOGITS
     이러한
    0.41
     materialism
    0.39
     wrongdoing
    0.39
    这一切
    0.39
     acest
    0.38
     wannan
    0.38
     przedsi
    0.37
    也許
    0.37
     aceste
    0.37
     idealism
    0.37
    Activations Density 8.323%

    No Known Activations