© 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. 119981
    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
    䀘
    -0.06
     or
    -0.06
     cij
    -0.05
     colon
    -0.05
    䄸
    -0.05
    䄪
    -0.05
     স্বাদ
    -0.05
    䊂
    -0.05
    euros
    -0.05
    㴌
    -0.05
    POSITIVE LOGITS
     gebruikt
    0.08
     utilisés
    0.07
    這
    0.07
    大切な
    0.07
     including
    0.07
     použí
    0.07
     sinnv
    0.07
     vitally
    0.07
     not
    0.07
     utilizados
    0.07
    Activations Density 0.000%

    No Known Activations