© 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. 120041
    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
    Last
    -0.07
     MUST
    -0.07
     ostatnich
    -0.07
    LAST
    -0.06
    ())
    -0.06
     послед
    -0.06
    last
    -0.06
     last
    -0.06
    上次
    -0.06
     Last
    -0.06
    POSITIVE LOGITS
     initializer
    0.06
    تحان
    0.06
     ł
    0.06
     precluded
    0.06
     હતો
    0.05
     वाट
    0.05
     eyelid
    0.05
     acreditar
    0.05
    ありました
    0.05
    वाड़ी
    0.05
    Activations Density 0.000%

    No Known Activations