© 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. 130292
    Prev
    Next
    INDEX
    Explanations

    Nebraska, Quantification, Certain medications

    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
     বিশ্বের
    -0.07
    匂
    -0.06
     transforms
    -0.06
     visible
    -0.06
     insbesondere
    -0.06
    യ
    -0.06
     soprattutto
    -0.06
     documento
    -0.06
     discover
    -0.06
     atteggi
    -0.06
    POSITIVE LOGITS
    вер
    0.06
     עבור
    0.06
    vox
    0.05
     glen
    0.05
     deduction
    0.05
    时刻
    0.05
    inger
    0.05
     lovely
    0.05
    是在
    0.05
     jaoks
    0.05
    Activations Density 0.001%

    No Known Activations