© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2730
    Prev
    Next
    INDEX
    Explanations

    data management, AI systems, animal kingdom

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

    The neuron identifies the main topic noun (the key subject word) that introduces or headlines each paragraph 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
    Refs
    0.58
    Xml
    0.56
    IfNeeded
    0.56
     якщо
    0.55
    Addr
    0.54
    Configs
    0.54
    /";
    0.52
    Urls
    0.52
     和
    0.52
    Suggestions
    0.52
    POSITIVE LOGITS
     epitome
    0.65
     alberga
    0.64
     estadounidense
    0.63
     adage
    0.63
     eldest
    0.63
     slogan
    0.62
    говор
    0.62
     রয়েছে
    0.61
     onus
    0.61
     infringer
    0.61
    Activations Density 0.189%

    No Known Activations