© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2853
    Prev
    Next
    INDEX
    Explanations

    specific non-English text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     आणि
    0.83
     (
    0.82
     and
    0.82
    ↵↵
    0.81
     এবং
    0.79
     substantial
    0.76
     ("
    0.74
     และ
    0.73
     और
    0.73
     And
    0.73
    POSITIVE LOGITS
     erreur
    0.79
    某个
    0.78
     ошибка
    0.78
     komentar
    0.78
     verletzt
    0.77
    ?]
    0.77
     refute
    0.76
    解决方法
    0.75
     الوز
    0.74
    ]?
    0.74
    Activations Density 0.443%

    No Known Activations