© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12566
    Prev
    Next
    INDEX
    Explanations

    notes outline uml

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

    The neuron activates specifically on the word “Notes,” flagging section headings labeled as notes.

    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_31_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
    <h4>
    0.68
     ٣
    0.61
    <h3>
    0.58
     宮
    0.58
     ৩
    0.58
     న
    0.57
    <a>
    0.57
     ,
    0.57
    </td>
    0.56
     från
    0.55
    POSITIVE LOGITS
    চ্ছিলাম
    0.61
    <start_of_image>
    0.61
    linestyle
    0.59
    тивных
    0.58
    也有
    0.57
    풉
    0.57
    DOWNLOAD
    0.57
     hydrophilic
    0.57
    シンプルな
    0.57
    犟
    0.57
    Activations Density 0.000%

    No Known Activations