© 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. 117687
    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
     for
    -0.06
    !!!!
    -0.06
     For
    -0.06
    attro
    -0.06
     करके
    -0.06
     apni
    -0.06
     شخصی
    -0.06
    !!!!!!
    -0.06
     म्यूजिक
    -0.06
    对其
    -0.06
    POSITIVE LOGITS
     уже
    0.06
    SDAY
    0.06
     మొద
    0.06
     той
    0.06
    chemy
    0.06
    ान्य
    0.06
    とし
    0.06
     ως
    0.06
     already
    0.06
     Reihe
    0.06
    Activations Density 0.000%

    No Known Activations