© 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. 6554
    Prev
    Next
    INDEX
    Explanations

    business diagram

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

    The neuron responds strongly to technical identifiers—acronyms, model numbers, numeric codes, and other specialized instrumentation or protocol terms.

    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
     ɛ
    0.75
     되
    0.73
     অর্থনীতি
    0.73
     Eulerian
    0.70
     分析
    0.70
    ्‍यादा
    0.70
    ена
    0.68
     父
    0.67
     当
    0.67
    üglich
    0.67
    POSITIVE LOGITS
     সর্ব
    0.82
    ותו
    0.79
    *
    0.78
    *}\
    0.77
     sıra
    0.75
    ['-
    0.74
    Revision
    0.73
     istot
    0.73
    
    0.73
    রূপে
    0.72
    Activations Density 0.001%

    No Known Activations