© 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. 128650
    Prev
    Next
    INDEX
    Explanations

    division within parentheses

    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
     tangan
    -0.07
    两种
    -0.06
     ముందు
    -0.06
     দুপুরে
    -0.06
     জন্য
    -0.06
    兩種
    -0.06
     گلوکار
    -0.06
     doua
    -0.06
    хов
    -0.05
     পালন
    -0.05
    POSITIVE LOGITS
    Insider
    0.07
     the
    0.07
     नियो
    0.06
     njegov
    0.06
     his
    0.06
    iš
    0.06
     wanted
    0.06
     그의
    0.06
     핵심
    0.06
     hänen
    0.06
    Activations Density 0.003%

    No Known Activations