© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    start of phrase

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

    The neuron strongly activates on standalone decimal‐formatted numbers (e.g. DOIs, page or volume identifiers).

    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
    分为
    0.81
    ↵
    0.75
    的主
    0.73
    業
    0.70
    分為
    0.69
    生活
    0.68
    的小
    0.68
    じ
    0.68
    브
    0.68
    美女
    0.67
    POSITIVE LOGITS
     повлия
    0.84
    வதை
    0.81
     idé
    0.78
     podía
    0.77
     convierte
    0.77
     καλύτε
    0.77
     esophageal
    0.77
     samud
    0.77
     рост
    0.76
     detonation
    0.76
    Activations Density 0.000%

    No Known Activations