© 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. 130015
    Prev
    Next
    INDEX
    Explanations

    render pdf pdf configurations

    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
     neemt
    -0.06
     Lec
    -0.06
     काप
    -0.05
     FTP
    -0.05
     Работа
    -0.05
     classed
    -0.05
     ChIP
    -0.05
    ISION
    -0.05
    чера
    -0.05
     quản
    -0.05
    POSITIVE LOGITS
    ్రీన్
    0.07
     configurations
    0.07
    釀
    0.06
     ಪ್ರಯೋಜನ
    0.06
     лай
    0.06
    生成的
    0.06
     похо
    0.06
     रोजी
    0.06
     produced
    0.06
     generated
    0.06
    Activations Density 0.071%

    No Known Activations