© 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. 1403
    Prev
    Next
    INDEX
    Explanations

    The neuron flags unusually infrequent or distinctive words in the text.

    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
     、,
    0.83
    یں۔
    0.78
     ہوا۔
    0.76
    、「
    0.75
    €.
    0.73
    ógio
    0.73
     ہے۔
    0.72
    ል።
    0.70
     。,
    0.68
    _,
    0.68
    POSITIVE LOGITS
     aka
    0.96
     [
    0.90
     AKA
    0.82
     Diarsipkan
    0.79
     [§
    0.78
     [(
    0.77
     (
    0.75
     {
    0.75
     (.
    0.73
     including
    0.73
    Activations Density 0.377%

    No Known Activations