© 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. 129041
    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
     λόγω
    -0.07
    を含む
    -0.07
     తెలి
    -0.06
    nań
    -0.06
     सीमित
    -0.06
    служ
    -0.06
    说了
    -0.06
     限定
    -0.06
    方式
    -0.06
    若い
    -0.06
    POSITIVE LOGITS
     sowas
    0.07
     Creating
    0.06
    ola
    0.06
     ostensibly
    0.06
     burgeoning
    0.06
     monstrous
    0.06
    compens
    0.06
     creates
    0.06
     renowned
    0.05
     เครื่อง
    0.05
    Activations Density 0.000%

    No Known Activations