© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the discourse marker “reason” (and its plural “reasons”), i.e. it detects when the text introduces an explanation.

    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
     }}=
    0.56
    }}=
    0.51
    )}=
    0.49
    blätter
    0.48
    })=\
    0.47
     katika
    0.47
     وصحبه
    0.47
     dovrà
    0.46
    }={
    0.46
    ジェクト
    0.46
    POSITIVE LOGITS
     why
    5.03
    why
    4.78
     WHY
    4.44
    为什么
    4.41
    Why
    4.38
     Why
    4.34
    WHY
    4.28
     pourquoi
    4.22
     warum
    4.19
     왜
    4.09
    Activations Density 1.057%

    No Known Activations