© 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. 117123
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
     वजह
    -0.06
     dvije
    -0.06
     독
    -0.06
    طلاب
    -0.06
     потому
    -0.06
    獨
    -0.06
     zbog
    -0.06
     jeans
    -0.06
     خودم
    -0.06
    
    -0.06
    POSITIVE LOGITS
     કાર્યવાહી
    0.06
    Diet
    0.05
    IamPolicy
    0.05
     सल्ला
    0.05
    يث
    0.05
    watchlist
    0.05
     চিকিত
    0.05
    Experiences
    0.05
    eto
    0.05
     এখানেই
    0.05
    Activations Density 0.005%

    No Known Activations