© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on token fragments beginning with “Per,” i.e. words or names that start with the letters P-e-r.

    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
     Heidelberg
    0.59
    जेश
    0.58
    ヾ
    0.58
    ríklad
    0.57
     Santander
    0.56
     メーカー
    0.54
    גיע
    0.54
    茜
    0.54
     Kew
    0.53
     Habsburg
    0.53
    POSITIVE LOGITS
     PER
    0.80
     퍼
    0.73
     diem
    0.72
     Пер
    0.71
    uvian
    0.71
    Per
    0.71
     Perk
    0.70
    ंबू
    0.70
    \!\
    0.70
    haj
    0.69
    Activations Density 0.204%

    No Known Activations