© 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. 120186
    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
     adhere
    -0.07
     zcela
    -0.06
     integer
    -0.06
     cannot
    -0.06
     extinguish
    -0.06
     unfounded
    -0.06
     you
    -0.06
     didn
    -0.06
    Riga
    -0.06
     فاذا
    -0.06
    POSITIVE LOGITS
    पू
    0.06
     sujeto
    0.06
     pre
    0.06
     फ़
    0.06
     Meister
    0.06
     înainte
    0.06
    AB
    0.06
     các
    0.05
    emporary
    0.05
    ):
    0.05
    Activations Density 0.000%

    No Known Activations