© 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. 117512
    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
     нами
    -0.06
     hre
    -0.06
     ними
    -0.06
     (!)
    -0.06
    here
    -0.05
     言っ
    -0.05
     Unified
    -0.05
    现代化
    -0.05
     might
    -0.05
    もあります
    -0.05
    POSITIVE LOGITS
    ＋
    0.07
     thỏa
    0.06
    與
    0.06
     yaml
    0.06
     BEFORE
    0.06
    与
    0.06
     sogenannten
    0.06
     devido
    0.06
    lässlich
    0.06
     BECAUSE
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.