© 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. 129446
    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
    ?
    -0.06
     three
    -0.05
    ोटा
    -0.05
    gte
    -0.05
     set
    -0.05
    Ø
    -0.05
    three
    -0.05
     high
    -0.05
     পুনঃ
    -0.05
     sheer
    -0.05
    POSITIVE LOGITS
     اغلب
    0.07
     vermutlich
    0.06
     WHICH
    0.06
    iremos
    0.06
    整个
    0.06
     indicted
    0.06
     langt
    0.06
    仕事
    0.06
     мае
    0.06
    那個
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.