© 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. 129315
    Prev
    Next
    INDEX
    Explanations

    links and how-tos

    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
     آنچه
    -0.07
     обществе
    -0.07
     innovation
    -0.06
     पुण्य
    -0.06
     megold
    -0.06
     NOW
    -0.06
    NOW
    -0.06
    দন
    -0.06
     शिक्षक
    -0.06
     seçenek
    -0.06
    POSITIVE LOGITS
     jejich
    0.07
    عمل
    0.06
     tampoco
    0.06
                
    0.06
     these
    0.06
     any
    0.06
     previous
    0.06
     دائما
    0.06
    result
    0.06
     これらの
    0.06
    Activations Density 0.007%

    No Known Activations