© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7806
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

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

    The neuron flags individual list‐item terms—especially nouns in enumerations or instructions (e.g. recipe ingredients or technical specs).

    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
     –,
    1.87
     🙌
    1.63
     🌱
    1.55
     🤗
    1.53
     —,
    1.52
     👀
    1.51
     États
    1.48
     💞
    1.48
     ℝ
    1.47
     Rodríguez
    1.46
    POSITIVE LOGITS
    =
    2.08
    ==
    1.77
    =(
    1.71
    (
    1.62
    <=
    1.61
    (()=>{
    1.61
    =>
    1.53
    =[
    1.52
    ()=>{
    1.51
    !=
    1.48
    Activations Density 0.177%

    No Known Activations