© 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. 128811
    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
    Only
    -0.06
     रजिस्ट
    -0.06
     qualquer
    -0.06
     వైసీపీ
    -0.06
     वडिला
    -0.06
     WOR
    -0.06
     această
    -0.06
    のみ
    -0.06
     malos
    -0.05
     podrá
    -0.05
    POSITIVE LOGITS
     gerade
    0.06
    挖掘
    0.06
    今回
    0.06
    ضور
    0.05
     vigour
    0.05
    焚
    0.05
     eigenlijk
    0.05
     사실
    0.05
     Chai
    0.05
    美味し
    0.05
    Activations Density 0.000%

    No Known Activations