© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2316
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "__main__": main()

    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_17_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
     Plast
    0.82
     Op
    0.77
    塑料
    0.77
    温泉
    0.75
    Entre
    0.74
    Op
    0.74
    兩種
    0.73
     욕
    0.73
     Entre
    0.73
     Plastic
    0.72
    POSITIVE LOGITS
     significant
    0.61
    CHANGED
    0.61
     wzrost
    0.60
     Bragg
    0.59
     khấu
    0.59
    ாதார
    0.59
     grown
    0.59
     दीक्षित
    0.59
    significant
    0.59
    instag
    0.58
    Activations Density 0.091%

    No Known Activations