© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4969
    Prev
    Next
    INDEX
    Explanations

    long-term outcomes and planning

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

    This neuron strongly activates on the word “term,” especially when it appears in hyphenated duration phrases (e.g. “short-term” or “long-term”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    UARY
    0.64
    féle
    0.64
    빛
    0.61
    sonian
    0.59
    圳
    0.59
    第一时间
    0.56
    式
    0.55
     monde
    0.53
     वाक्य
    0.53
    ائيل
    0.53
    POSITIVE LOGITS
     (>
    0.84
     (\<
    0.75
     incentives
    0.70
     (<
    0.70
     $(<
    0.64
     '<
    0.61
     energet
    0.61
     طويلة
    0.61
    规划
    0.60
     caching
    0.60
    Activations Density 0.249%

    No Known Activations