© 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. 8691
    Prev
    Next
    INDEX
    Explanations

    foreign languages and terms

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

    The neuron strongly responds to tokens in customer‐service inquiries around ordering—especially words about payment methods, shipping or receiving an order.

    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
    令和
    0.84
    ُ
    0.77
    /
    0.76
    <0xF0>
    0.75
    <0xEB>
    0.71
    ໜ
    0.71
    ڤ
    0.70
    <0xC2>
    0.68
     LGBTQ
    0.68
     проє
    0.68
    POSITIVE LOGITS
     সঙ্গে
    1.05
     पासून
    0.94
     vérifier
    0.94
     ਨੂੰ
    0.91
     numai
    0.90
     différente
    0.90
     لئے
    0.90
     তোলে
    0.89
    ట్స్‌మన్
    0.89
     acquistare
    0.89
    Activations Density 0.713%

    No Known Activations