© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on the token “Young,” especially when it appears as a capitalized title.

    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
     vscode
    0.66
     دروس
    0.61
     halftone
    0.58
     hak
    0.57
     cosmetic
    0.56
     फ्र
    0.54
     რ
    0.54
    akk
    0.54
     বুল
    0.54
     đ
    0.53
    POSITIVE LOGITS
    Fellow
    0.62
    debris
    0.62
    Men
    0.59
    Rapid
    0.56
    discharge
    0.54
     Discharge
    0.54
     Men
    0.53
    Previously
    0.53
    lodge
    0.53
    RefManager
    0.52
    Activations Density 0.000%

    No Known Activations