© 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-262K
    7. 34718
    Prev
    Next
    INDEX
    Explanations

    inappropriate language detection

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    មី
    0.84
     ujar
    0.82
     isol
    0.80
     greenhouses
    0.79
    吺
    0.78
     wetland
    0.76
    facts
    0.74
    Mechanical
    0.73
     isole
    0.73
     idioms
    0.73
    POSITIVE LOGITS
    ↵
    0.95
     다른
    0.91
     너
    0.89
     самая
    0.89
    が入
    0.88
    이션
    0.86
     razão
    0.85
     소
    0.84
     desempen
    0.83
     Соответ
    0.82
    Activations Density 0.000%

    No Known Activations