© 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. 119507
    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
     alcun
    -0.06
     outlying
    -0.06
     Palaiseau
    -0.06
    |$
    -0.06
     extol
    -0.06
     परप
    -0.06
    Popover
    -0.06
     Inverness
    -0.06
    honneur
    -0.06
     unexpectedly
    -0.06
    POSITIVE LOGITS
     devraient
    0.06
     and
    0.06
    ब्रिट
    0.06
     !!!!
    0.06
     створення
    0.06
     !!!
    0.06
     تفسیر
    0.06
    pure
    0.06
    কবি
    0.06
     alın
    0.06
    Activations Density 0.000%

    No Known Activations