© 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. 6694
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    This neuron strongly activates on proper nouns and named entities—especially historical people, places, clans, and institutions.

    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
    ,
    0.78
    ,?
    0.63
    aka
    0.63
     देखील
    0.62
    ،
    0.61
    AKA
    0.59
     efficiently
    0.59
     promptly
    0.59
     العديد
    0.59
    ,‎
    0.59
    POSITIVE LOGITS
     viz
    0.84
    being
    0.80
    viz
    0.79
     אבל
    0.73
    เพราะ
    0.73
     ибо
    0.72
     protože
    0.70
     çünkü
    0.69
    ถ้า
    0.68
     rzeczyw
    0.68
    Activations Density 0.086%

    No Known Activations