© 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. 117490
    Prev
    Next
    INDEX
    Explanations

    date/time and metadata

    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
    irão
    -0.07
     quantized
    -0.07
    であれば
    -0.06
     acompañado
    -0.06
     litro
    -0.06
    जामा
    -0.06
     zajedno
    -0.06
     kilow
    -0.06
     Système
    -0.06
     norme
    -0.06
    POSITIVE LOGITS
     may
    0.07
     Г
    0.07
     ss
    0.06
           
    0.05
     не
    0.05
     puede
    0.05
    你不
    0.05
     ihr
    0.05
     includes
    0.05
     डिजाइनर
    0.05
    Activations Density 0.001%

    No Known Activations