© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6451
    Prev
    Next
    INDEX
    Explanations

    century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ي
    2.31
    ات
    2.20
    s
    2.19
    y
    2.09
    י
    2.09
     таки
    2.08
    ع
    2.08
    arono
    2.03
    ა
    1.88
    ээр
    1.87
    POSITIVE LOGITS
     accolades
    2.05
     undermined
    2.03
     undermine
    2.00
     undermines
    2.00
     acclaimed
    1.90
    ventions
    1.89
     defies
    1.77
     carcinomas
    1.73
     peonies
    1.71
    てください
    1.70
    Activations Density 0.008%

    No Known Activations