© 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. 128952
    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
     वारदात
    -0.07
     wary
    -0.06
    গানি
    -0.06
     have
    -0.06
     എന്നീ
    -0.06
     পিছিয়ে
    -0.06
     リ
    -0.06
     enquiry
    -0.06
    running
    -0.06
    是有
    -0.06
    POSITIVE LOGITS
     nadie
    0.06
     معمولی
    0.06
     niets
    0.06
     никто
    0.06
     единственный
    0.06
    ról
    0.06
     addition
    0.06
    dasarkan
    0.06
     ничего
    0.06
     если
    0.06
    Activations Density 0.000%

    No Known Activations