© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2198
    Prev
    Next
    INDEX
    Explanations

    regularly spending time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
     result
    1.15
    成り立つ
    0.98
    場合の
    0.94
     results
    0.91
    持つ
    0.90
     resul
    0.90
    result
    0.89
    лыгы
    0.88
    ]').
    0.87
     sonucu
    0.87
    POSITIVE LOGITS
     каждый
    1.90
     meticul
    1.84
    ствуйте
    1.84
     подроб
    1.80
     дета
    1.79
     поговори
    1.78
     každý
    1.78
     всеки
    1.78
     протяжении
    1.77
     регулярно
    1.76
    Activations Density 0.499%

    No Known Activations