© 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. 10259
    Prev
    Next
    INDEX
    Explanations

    property management

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

    This neuron fires on references to Pinterest image collections or links, i.e. list-style Pinterest URLs.

    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
    ER
    0.86
    j
    0.84
    EL
    0.84
    laşt
    0.81
    J
    0.80
    Ğ
    0.79
    ä
    0.79
    ⊢
    0.78
    첸
    0.75
    Di
    0.75
    POSITIVE LOGITS
     Adhesive
    0.93
     насла
    0.78
    ЗИ
    0.78
     ограниче
    0.77
     дана
    0.77
    зонта
    0.75
     SupCt
    0.74
     повре
    0.74
     ممن
    0.73
     голова
    0.73
    Activations Density 0.000%

    No Known Activations