© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130118
    Prev
    Next
    INDEX
    Explanations

    star character in code

    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
    ოლი
    -0.07
     रखिए
    -0.06
     Clicking
    -0.06
     Chúng
    -0.06
     ње
    -0.06
     તેમના
    -0.06
    Ketika
    -0.06
     عندما
    -0.06
     tại
    -0.06
    .:
    -0.06
    POSITIVE LOGITS
     jedynie
    0.07
     CL
    0.06
     merely
    0.06
    another
    0.06
    ounding
    0.06
    oppable
    0.06
     ৪০০
    0.05
     விழ
    0.05
     character
    0.05
     छा
    0.05
    Activations Density 0.003%

    No Known Activations