© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129257
    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
    듯
    -0.06
     ওয়াল
    -0.06
     the
    -0.06
     followed
    -0.06
     Begriff
    -0.06
     böyle
    -0.06
    ગે
    -0.06
    izacion
    -0.06
    지원
    -0.06
     অদৃশ্য
    -0.06
    POSITIVE LOGITS
    TypeScript
    0.07
     Largest
    0.07
     मिलाने
    0.06
     крупней
    0.06
     Descriptive
    0.06
     tricked
    0.06
     lässt
    0.06
    を含む
    0.06
     largest
    0.06
    ADO
    0.06
    Activations Density 0.000%

    No Known Activations