© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9414
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Pla
    0.59
     Зна
    0.58
    حد
    0.56
     後
    0.55
     Universit
    0.55
    ﾌ
    0.55
     Canadiens
    0.55
     تحديد
    0.55
     извър
    0.54
     夏
    0.54
    POSITIVE LOGITS
     pakaian
    0.93
     på
    0.93
     pantai
    0.86
     peligro
    0.85
    På
    0.84
     poitrine
    0.83
     palabras
    0.81
     Pferde
    0.80
     पश्चिम
    0.79
     pelajaran
    0.79
    Activations Density 3.000%

    No Known Activations