© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130923
    Prev
    Next
    INDEX
    Explanations

    Arabidopsis thaliana amino acid

    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
    ждая
    -0.06
    Pem
    -0.06
     greatest
    -0.06
    jazz
    -0.06
     Pem
    -0.06
     случаев
    -0.06
    ħ
    -0.06
    🗝
    -0.06
     respecto
    -0.06
     हरिद्वार
    -0.06
    POSITIVE LOGITS
     içerisinde
    0.06
    ⚫
    0.06
    ಗೊಳ್ಳ
    0.06
     ⚫
    0.06
     Arabidopsis
    0.05
     দৈর্ঘ
    0.05
     preparing
    0.05
    рам
    0.05
     wrongdoing
    0.05
     Washington
    0.05
    Activations Density 0.009%

    No Known Activations