© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    **reason why**

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

    The neuron detects occurrences of the word “reason” (and its morphological variants such as “reasonable,” “reasonably,” etc.).

    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
    gür
    0.63
    för
    0.59
     unwa
    0.59
    <0xED>
    0.59
     peptid
    0.59
    sächlich
    0.59
    వర్
    0.58
     konusu
    0.57
     reproduc
    0.57
     Controvers
    0.57
    POSITIVE LOGITS
     बताओ
    0.83
    ableness
    0.66
    cultured
    0.66
    ﺪ
    0.66
    Prox
    0.63
    ငံ
    0.62
    ISAM
    0.62
    បញ្ចូល
    0.61
    EE
    0.59
    checkout
    0.59
    Activations Density 0.082%

    No Known Activations