© 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. 129501
    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
    änt
    -0.06
    era
    -0.06
     значит
    -0.06
    보다
    -0.06
     Sam
    -0.06
     Ar
    -0.06
     ഗ്ര
    -0.06
    фек
    -0.05
    rss
    -0.05
    終於
    -0.05
    POSITIVE LOGITS
     old
    0.06
     erstwhile
    0.06
    多次
    0.06
    是在
    0.06
     Tots
    0.06
     recouvert
    0.06
     ได้
    0.06
     exclusion
    0.06
    Pressed
    0.05
     gamle
    0.05
    Activations Density 0.000%

    No Known Activations