© 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. 117589
    Prev
    Next
    INDEX
    Explanations

    differential staining

    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
     boxes
    -0.07
     rained
    -0.06
     लकड़ी
    -0.06
    建築
    -0.06
     камен
    -0.06
     colegio
    -0.06
     इमार
    -0.06
    โรง
    -0.06
     石
    -0.06
    ","#
    -0.06
    POSITIVE LOGITS
     nedir
    0.06
     légumes
    0.06
    plan
    0.06
    afood
    0.06
     Delhi
    0.06
    นิด
    0.06
     Foods
    0.06
     priority
    0.06
     lovable
    0.06
     الغذ
    0.06
    Activations Density 0.005%

    No Known Activations