© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128731
    Prev
    Next
    INDEX
    Explanations

    developer console commands

    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
    दर्शी
    -0.06
    हीन
    -0.06
    ിലേ
    -0.06
    kannya
    -0.06
     Expt
    -0.06
     caricature
    -0.06
     continued
    -0.06
    ლი
    -0.06
     deterred
    -0.06
     član
    -0.06
    POSITIVE LOGITS
    সমাজের
    0.06
           
    0.06
    sg
    0.06
    ensely
    0.05
     পাচ্ছি
    0.05
     Optimization
    0.05
     जिम्मेदार
    0.05
     โดย
    0.05
    addy
    0.05
     Optimized
    0.05
    Activations Density 0.011%

    No Known Activations