© 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. 128972
    Prev
    Next
    INDEX
    Explanations

    class and data structures

    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
     functioning
    -0.06
     guia
    -0.06
     slain
    -0.06
     ক্রয়
    -0.06
     साठी
    -0.06
    Jenis
    -0.06
     guides
    -0.06
     guide
    -0.06
     conclusive
    -0.06
    Mord
    -0.06
    POSITIVE LOGITS
     magnificent
    0.06
     bead
    0.06
    soap
    0.06
     अधिवक्ता
    0.06
     Significant
    0.06
     slightly
    0.06
     дизайне
    0.06
     attorneys
    0.06
    بة
    0.06
     ιστο
    0.06
    Activations Density 0.072%

    No Known Activations