© 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. 130061
    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
     हम
    -0.07
     understand
    -0.06
     sæ
    -0.06
     what
    -0.06
     müssen
    -0.06
     shitty
    -0.06
    🐨
    -0.06
    会对
    -0.06
     wee
    -0.06
     последнее
    -0.06
    POSITIVE LOGITS
     thậm
    0.07
     or
    0.06
     with
    0.06
     bahkan
    0.06
     nawet
    0.06
    甚至
    0.06
     even
    0.06
     incluso
    0.06
     அல்லது
    0.06
     pouvant
    0.06
    Activations Density 0.000%

    No Known Activations