© 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. 120430
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Muitos
    -0.07
     muchos
    -0.07
     algunos
    -0.07
     algunas
    -0.07
     подрост
    -0.07
     이름
    -0.07
     வெவ்வேறு
    -0.07
    ্যালেঞ্জ
    -0.06
     دادن
    -0.06
     अमीर
    -0.06
    POSITIVE LOGITS
     باشید
    0.06
     તથા
    0.06
    ♥️
    0.06
     enchanting
    0.05
     extend
    0.05
     ebay
    0.05
    сную
    0.05
    不会
    0.05
     cornea
    0.05
     আস্তে
    0.05
    Activations Density 0.000%

    No Known Activations