© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15865
    Prev
    Next
    INDEX
    Explanations

    severe dental

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

    The main thing this neuron does is pick out numeric technical specifications (measurements, dimensions, and units).

    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_31_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
    ُ
    0.86
    <0xF0>
    0.84
     ChatGPT
    0.83
    ನ್‌
    0.79
     inclusivity
    0.78
    TikTok
    0.78
    🧔
    0.78
     TikTok
    0.77
     ২০২২
    0.75
    ChatGPT
    0.75
    POSITIVE LOGITS
     সঙ্গে
    0.93
    ോ
    0.89
     اثنين
    0.85
     katika
    0.84
     belangrijkste
    0.83
     pelayanan
    0.82
     bahwa
    0.82
     gleichen
    0.82
     trzeba
    0.80
     एंड्रॉयड
    0.80
    Activations Density 0.621%

    No Known Activations