© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14472
    Prev
    Next
    INDEX
    Explanations

    company or product names

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

    The neuron flags numeric expressions—tokens representing numbers, dates, counts, and other digit‐based quantities.

    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
    0.90
    非常的
    0.89
    そして
    0.85
     Whilst
    0.82
    很多的
    0.80
     हेतु
    0.79
    今後の
    0.77
     tutaj
    0.76
     समस्त
    0.75
    まさに
    0.75
    POSITIVE LOGITS
     yüzde
    0.83
     spokeswoman
    0.83
     最初
    0.79
     지난해
    0.75
     yaklaşık
    0.75
     loosely
    0.73
     dozens
    0.72
     说
    0.71
     सुमारे
    0.71
     reportedly
    0.71
    Activations Density 0.508%

    No Known Activations