© 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. 7348
    Prev
    Next
    INDEX
    Explanations

    learned mastering habit

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

    This neuron responds to instructional or educational language about learning to read or write code.

    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
    ේශ
    0.61
    ві
    0.58
    ทรัพย์
    0.57
     candles
    0.55
     gd
    0.54
     العق
    0.54
    첵
    0.53
     ESTATE
    0.51
     provocative
    0.51
     имуще
    0.51
    POSITIVE LOGITS
    慣
    1.81
     mastered
    1.80
     aprender
    1.77
     mastering
    1.73
     연습
    1.73
    練習
    1.72
     learning
    1.70
    學習
    1.70
     привы
    1.70
    习惯
    1.66
    Activations Density 0.819%

    No Known Activations