© 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. 69
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or ranges

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

    This neuron specializes in detecting standalone numeric tokens (e.g. measurements, percentages, and other numbers) 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
    quele
    0.26
    ва
    0.25
    zelfde
    0.25
    ور
    0.24
    erver
    0.23
    ن
    0.23
    ка
    0.23
    ו
    0.22
     CreateWindow
    0.22
    গুলির
    0.22
    POSITIVE LOGITS
    ️⃣
    0.26
    two
    0.25
    ºC
    0.25
     thousand
    0.24
    ère
    0.23
    stö
    0.22
    xbet
    0.22
     million
    0.21
     vài
    0.21
     tablespoons
    0.21
    Activations Density 0.868%

    No Known Activations