© 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. 116754
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with numbers

    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
     ثلاث
    -0.06
                
    -0.06
     each
    -0.06
     between
    -0.06
     ثلاثة
    -0.06
     您
    -0.06
     trzy
    -0.06
     छह
    -0.06
        
    -0.06
     প্রতিটি
    -0.06
    POSITIVE LOGITS
     what
    0.08
     aquilo
    0.07
     ceea
    0.06
     форм
    0.06
     ciò
    0.06
     დას
    0.06
    先日
    0.06
     součástí
    0.06
     Dien
    0.06
     consultative
    0.06
    Activations Density 0.005%

    No Known Activations