© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    ,

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

    The neuron strongly activates on named entities and technical terms—especially trademarked product names, personal or place names, software titles, and other specialized jargon.

    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
    冫
    0.61
    玼
    0.59
    𒅌
    0.57
    dataPro
    0.55
    プレゼ
    0.52
    惀
    0.52
     UnitTest
    0.51
    dataIn
    0.50
    ពិស
    0.50
     заболе
    0.49
    POSITIVE LOGITS
     They
    0.58
    org
    0.54
     com
    0.54
    com
    0.53
     they
    0.52
     is
    0.51
     See
    0.51
    They
    0.50
    ?
    0.49
    į
    0.49
    Activations Density 0.041%

    No Known Activations