© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11338
    Prev
    Next
    INDEX
    Explanations

    enum class definitions

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

    The neuron detects product specification or attribute labels (e.g. “Brand name,” “Item specifics,” “Unit type,” “Pattern,” “Made in China,” “Age range,” etc.) in e-commerce style listings.

    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
    InputValue
    0.68
    Url
    0.62
    url
    0.62
    Susp
    0.60
    아요
    0.59
    <0xE3>
    0.58
    =''
    0.58
    />
    0.57
    Спо
    0.57
    熾
    0.57
    POSITIVE LOGITS
     certes
    0.63
     regulars
    0.62
     Diocese
    0.62
     penguins
    0.61
     captives
    0.60
     drags
    0.60
     diocese
    0.59
     ersten
    0.58
    نګه
    0.58
     FTSE
    0.58
    Activations Density 0.001%

    No Known Activations