© 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. 6040
    Prev
    Next
    INDEX
    Explanations

    similar questions or prompts

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

    The neuron fires on section headings or links that point to related or “other” items (e.g. “other questions,” “related questions,” “compare to similar…”).

    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
     отсутствии
    0.62
    ствии
    0.59
    感觉到
    0.59
    );\
    0.57
    );*/
    0.57
    ),\
    0.57
     defocus
    0.55
    MainActivityTest
    0.55
     oblivion
    0.54
     decrement
    0.54
    POSITIVE LOGITS
    ó
    0.57
    ä
    0.55
    ب
    0.54
    ا
    0.53
    い
    0.53
    mari
    0.52
    猗
    0.52
    が含ま
    0.52
    mi
    0.51
    ă
    0.51
    Activations Density 0.000%

    No Known Activations