© 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. 5797
    Prev
    Next
    INDEX
    Explanations

    events initiated by someone or at a time

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

    The neuron primarily responds to numeric tokens (e.g. dates, ages, measurements) in the text.

    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
    ਹੀਂ
    0.54
    तियां
    0.52
    涵盖
    0.52
    ਵ
    0.52
     €,
    0.52
    िक्सल
    0.52
     proliferate
    0.52
    謦
    0.52
     recetas
    0.51
    ग्नो
    0.51
    POSITIVE LOGITS
     on
    0.90
     in
    0.87
    ใน
    0.75
     في
    0.70
     στο
    0.70
     στη
    0.68
     by
    0.68
     with
    0.67
     ใน
    0.66
     în
    0.66
    Activations Density 0.076%

    No Known Activations