© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    think step by step

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

    The neuron fires on words that express the act of thinking or reflecting (e.g. “think,” “thinking,” “consider,” “thought”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    imperative verbs or phrases prompting the reader to consider, contemplate, or mentally process something.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language about thinking, reflection, and consideration, especially directives or statements urging someone to think or consider something

    oai_token-act-pair · gpt-5Triggered 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
    TextAppearance
    0.65
     fő
    0.64
    数据显示
    0.63
     ẹ
    0.63
    워서
    0.59
     eloquently
    0.59
    বুঝ
    0.57
     রক্ষ
    0.56
    监听
    0.56
    宗旨
    0.56
    POSITIVE LOGITS
     Think
    1.08
     think
    1.07
    Think
    1.00
     THINK
    0.94
    think
    0.92
     थिंक
    0.89
     Thinking
    0.89
    চিন্ত
    0.84
     thinks
    0.84
    Thinking
    0.81
    Activations Density 0.213%

    No Known Activations