© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    sum of digits

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

    The neuron fires on standalone content‐words used as labels or headings (the main topic word of list items, section titles, or bullet points).

    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
    $)$.
    0.68
     )।
    0.65
     लेट्स
    0.64
     постара
    0.64
     شناخته
    0.63
     مختلفة
    0.62
    ቖ
    0.62
     personnels
    0.62
     مختلف
    0.61
     distintos
    0.61
    POSITIVE LOGITS
    la
    1.04
    ła
    0.86
    λα
    0.86
    ği
    0.86
    ların
    0.85
    ędzynarod
    0.84
    likle
    0.82
     yılında
    0.81
    ۤ
    0.80
    La
    0.79
    Activations Density 0.003%

    No Known Activations