© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15937
    Prev
    Next
    INDEX
    Explanations

    address abbreviations and types

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

    The neuron is highly activated by numeric tokens—especially floating‐point numbers or decimal‐style figures (e.g. volume/page numbers in citations).

    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
     
    0.81
     EMB
    0.76
    ut
    0.73
    ve
    0.73
    NING
    0.73
    ν
    0.72
     semblance
    0.71
    ELSE
    0.70
     revoke
    0.70
    ine
    0.69
    POSITIVE LOGITS
    ซึ่ง
    0.96
    種類
    0.92
    tipo
    0.84
     waarvan
    0.83
     које
    0.82
    tabla
    0.81
     chất
    0.80
    媜
    0.78
    ឈ្ម
    0.78
     ktorá
    0.77
    Activations Density 0.001%

    No Known Activations