© 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. 128313
    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
     ignoring
    -0.07
     ignores
    -0.07
    What
    -0.06
     arrogant
    -0.06
     becomes
    -0.06
    ក្ល
    -0.05
     then
    -0.05
     restocking
    -0.05
    ema
    -0.05
     blossoming
    -0.05
    POSITIVE LOGITS
     facilitar
    0.07
     vuonna
    0.06
     دو
    0.06
     favoriser
    0.06
     SUCH
    0.06
     రెండు
    0.06
    ımız
    0.06
     такое
    0.06
    ğin
    0.06
     двух
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.