© 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. 129527
    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
     sleigh
    -0.07
    lemente
    -0.06
     awareness
    -0.06
     Doesn
    -0.06
     EPS
    -0.06
     P
    -0.06
     Somewhere
    -0.06
    )-
    -0.06
    সমা
    -0.05
     referencias
    -0.05
    POSITIVE LOGITS
     multiple
    0.07
     towering
    0.06
    multiple
    0.06
     நடிக்க
    0.06
    他に
    0.06
     போக்குவர
    0.06
     finir
    0.06
     unstructured
    0.06
     throttling
    0.06
     چکے
    0.06
    Activations Density 0.000%

    No Known Activations