© 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. 11212
    Prev
    Next
    INDEX
    Explanations

    intimate acts

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

    This neuron fires on the first content word of each new text segment, effectively marking the start of a new document or section.

    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
     население
    0.83
     дов
    0.77
    ју
    0.75
     হয়তো
    0.74
     глав
    0.73
    大小
    0.72
    િવસ
    0.71
    左
    0.71
    ຕິດຕ
    0.70
    ので
    0.70
    POSITIVE LOGITS
    up
    0.85
    cı
    0.84
    in
    0.79
    ar
    0.79
    ie
    0.77
    cional
    0.77
     teljes
    0.76
    bilir
    0.75
     ønsker
    0.75
    !`
    0.75
    Activations Density 0.000%

    No Known Activations