© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi

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

    the neuron detects marketing-style product or service feature/specification descriptions.

    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
     roky
    0.71
    transactions
    0.68
     النهائية
    0.66
     prosecutions
    0.63
    webElementXpaths
    0.63
     সম্বন্ধে
    0.63
    晦
    0.63
    xB
    0.62
    膜
    0.62
     profits
    0.61
    POSITIVE LOGITS
     amenities
    1.49
    配备
    1.30
     Amenities
    1.28
     disediakan
    1.20
     conveniences
    1.18
    を備
    1.16
     ausgestattet
    1.13
     toiletries
    1.11
     equipped
    1.08
     funzionalità
    1.08
    Activations Density 2.054%

    No Known Activations