© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118123
    Prev
    Next
    INDEX
    Explanations

    contract appeals, sclerotherapy, occluder, serum, Q&A, Ford

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chefs
    -0.06
     Contractor
    -0.05
    イベント
    -0.05
     utilising
    -0.05
    Flor
    -0.05
     சுற்றுச்சூழ
    -0.05
     FALSE
    -0.05
    Measurement
    -0.05
     বিপজ্জনক
    -0.05
     markup
    -0.05
    POSITIVE LOGITS
     ഓരോ
    0.07
     اکثریت
    0.07
    找到
    0.07
     लु
    0.06
     sekolah
    0.06
     എത്ര
    0.06
     gevonden
    0.06
     encuentran
    0.06
    ánto
    0.06
    一个个
    0.06
    Activations Density 0.001%

    No Known Activations