© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14843
    Prev
    Next
    INDEX
    Explanations

    programming articles and code

    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
     Selon
    0.57
    Near
    0.54
    Selon
    0.54
    adu
    0.54
    ádio
    0.54
     انجام
    0.53
    Overlap
    0.53
    擔
    0.53
    Setup
    0.52
    Composition
    0.52
    POSITIVE LOGITS
    转载
    0.87
    总结
    0.86
     MATLAB
    0.86
    csdn
    0.86
     matlab
    0.85
     OpenCV
    0.84
    这篇文章
    0.79
     java
    0.79
     Matlab
    0.78
     python
    0.77
    Activations Density 0.065%

    No Known Activations