© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117367
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    によっては
    -0.06
    洗濯
    -0.06
     bestätigt
    -0.05
    感恩
    -0.05
     series
    -0.05
     receptacle
    -0.05
     vele
    -0.05
    を確認
    -0.05
    tha
    -0.05
     consomm
    -0.05
    POSITIVE LOGITS
     навіть
    0.07
     nawet
    0.07
     набор
    0.07
     даже
    0.06
    দেশের
    0.06
     poaching
    0.06
    菌
    0.06
    必须
    0.06
    வைய
    0.06
    行的
    0.06
    Activations Density 0.000%

    No Known Activations