© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2618
    Prev
    Next
    INDEX
    Explanations

    keywords, lease, library, research

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

    The neuron is specialized to detect numeric tokens with decimal points (floating‐point numbers).

    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
     oure
    0.94
    žen
    0.70
    s
    0.70
    bye
    0.70
     পরাজিত
    0.70
     vse
    0.68
    ći
    0.68
    ప్పటి
    0.68
     FURTHER
    0.68
     ১
    0.67
    POSITIVE LOGITS
    信仰
    0.79
    ंदोल
    0.77
    gambar
    0.73
     overpowering
    0.71
    大陆
    0.71
    如果你
    0.70
    ोलिक
    0.70
    लू
    0.70
    漫畫
    0.69
     Compt
    0.69
    Activations Density 0.000%

    No Known Activations