© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6222
    Prev
    Next
    INDEX
    Explanations

    Flag to optimize - if no swaps occur in a pass, the list is sorted

    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_31_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
    则
    0.70
    ▂
    0.67
    拥有
    0.67
     deems
    0.66
    ಿನ
    0.66
     memiliki
    0.65
     ensures
    0.64
    টি
    0.64
    ⌯
    0.63
    则是
    0.63
    POSITIVE LOGITS
    first
    0.73
    こんな
    0.68
    Сейчас
    0.66
     lately
    0.65
    whole
    0.65
     전에
    0.64
    sometimes
    0.64
     거의
    0.64
    probably
    0.63
     אבל
    0.63
    Activations Density 0.004%

    No Known Activations