© 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. 117708
    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
    timelist
    -0.06
     already
    -0.06
     inclusivity
    -0.06
    женных
    -0.06
     bestimmten
    -0.06
    ,
    -0.06
     these
    -0.06
     ఉంది
    -0.06
    женный
    -0.05
     expected
    -0.05
    POSITIVE LOGITS
     гораздо
    0.07
     MUCH
    0.06
     по
    0.06
    。
    0.06
    遮
    0.06
     Though
    0.06
     у
    0.06
     by
    0.06
    Though
    0.06
    عا
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.