© 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. 11397
    Prev
    Next
    INDEX
    Explanations

    luckily, thankfully, fortunately

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on mentions of software applications (especially bundled or phone apps) and their features.

    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
    으로서
    0.57
    pkins
    0.56
     cioè
    0.54
     fulfil
    0.52
     yani
    0.51
    韻
    0.51
    즉
    0.50
    即
    0.50
     tedy
    0.49
     assim
    0.49
    POSITIVE LOGITS
     fortunately
    3.58
     luckily
    3.56
    Fortunately
    3.47
     Fortunately
    3.41
     thankfully
    3.41
    Thankfully
    3.41
    Luckily
    3.34
     Luckily
    3.33
     Thankfully
    3.30
    fortunately
    2.92
    Activations Density 0.311%

    No Known Activations