© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on prominent domain-specific or technical content nouns (jargon and key subject 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_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
    点は
    0.68
    झ्
    0.67
     सक्छ
    0.65
    不由
    0.63
     बनते
    0.62
     হয়
    0.61
    ன்மையான
    0.57
    ሏ
    0.57
    ոչ
    0.56
    쁠
    0.56
    POSITIVE LOGITS
     để
    4.47
     чтобы
    4.22
    เพื่อ
    4.09
     כדי
    3.95
     щоб
    3.91
    เพื่อให้
    3.89
     upang
    3.81
     เพื่อ
    3.73
     чтоб
    3.59
    ដើម្បី
    3.31
    Activations Density 3.392%

    No Known Activations