© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128550
    Prev
    Next
    INDEX
    Explanations

    business and institutional contexts

    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
     మొత్తం
    -0.07
     முக்கிய
    -0.07
     중요한
    -0.07
     belangrijkste
    -0.06
     बेंगल
    -0.06
     parental
    -0.06
    破壊
    -0.06
     добы
    -0.06
     важней
    -0.06
     predominant
    -0.06
    POSITIVE LOGITS
     with
    0.08
     avec
    0.06
    としては
    0.06
    ποτε
    0.06
    <b>
    0.06
    னுடன்
    0.05
     दूसरों
    0.05
    ıyorum
    0.05
     sürekli
    0.05
    として
    0.05
    Activations Density 0.029%

    No Known Activations