© 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. 117801
    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
    品番
    -0.06
     mungkin
    -0.06
    NEUTRON
    -0.06
     indetermin
    -0.06
     misschien
    -0.06
     talvez
    -0.06
     থাকবেন
    -0.06
     prawdopod
    -0.06
     մ
    -0.06
    情報は
    -0.06
    POSITIVE LOGITS
     spots
    0.06
    oughby
    0.05
     दृढ़
    0.05
     வளர்ச்சி
    0.05
    生日
    0.05
    spots
    0.05
    Season
    0.05
     liczba
    0.05
     chủng
    0.05
    与之
    0.05
    Activations Density 0.000%

    No Known Activations