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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    Chinese dynasties and philosophy

    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
     शक्यता
    0.77
     Batter
    0.76
    鸫
    0.74
     සමඟ
    0.74
    琿
    0.72
     বাংলাদেশি
    0.72
    鍝
    0.72
     Bangladeshi
    0.72
     बेंगलुरु
    0.72
    绁
    0.69
    POSITIVE LOGITS
     Sage
    0.70
     Generations
    0.62
     sage
    0.62
    ⚊
    0.62
     prescriptive
    0.60
    Sage
    0.60
     reunir
    0.59
    格
    0.58
     રચ
    0.57
    田
    0.57
    Activations Density 0.073%

    No Known Activations