© 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. 120071
    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
    개
    -0.07
    의
    -0.06
    को
    -0.06
     now
    -0.06
     از
    -0.06
    Now
    -0.06
    ский
    -0.05
     در
    -0.05
     represents
    -0.05
     लंबा
    -0.05
    POSITIVE LOGITS
    不但
    0.07
     televised
    0.06
    禮
    0.06
     voluntarily
    0.06
    ᠢ
    0.06
    给
    0.06
     MULT
    0.06
    ﮈ
    0.06
     όπου
    0.06
    メッセージ
    0.06
    Activations Density 0.000%

    No Known Activations