© 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. 12481
    Prev
    Next
    INDEX
    Explanations

    discussion problems and start laws

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

    The neuron activates on numeric tokens (especially decimal numbers and measurements).

    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
    ied
    0.72
    getahuan
    0.70
    rollees
    0.68
    ĭ
    0.66
    Historically
    0.66
     iStock
    0.64
    ool
    0.63
    ossen
    0.63
    radiol
    0.63
    claimed
    0.63
    POSITIVE LOGITS
    ا
    1.03
    י
    0.98
    ة
    0.89
    تور
    0.86
     особа
    0.85
    ساز
    0.81
    ת
    0.81
    ويس
    0.79
    مين
    0.79
    вос
    0.79
    Activations Density 0.000%

    No Known Activations