© 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. 116714
    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
     USGS
    -0.06
    separated
    -0.06
    പ്പോഴ
    -0.06
     বাস
    -0.06
    ಕ್ಕೂ
    -0.06
     Yamaguchi
    -0.05
    organisms
    -0.05
     FOLLOWING
    -0.05
    ANNOT
    -0.05
    ến
    -0.05
    POSITIVE LOGITS
     скорее
    0.07
    Remember
    0.07
     essendo
    0.07
    warte
    0.06
    Crime
    0.06
    🔓
    0.06
     fhe
    0.06
     детали
    0.06
    小时候
    0.06
    秥
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.