© 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. 129520
    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
     finally
    -0.07
    などを
    -0.07
    option
    -0.06
     наконец
    -0.06
     मादा
    -0.06
     Finally
    -0.06
     fleste
    -0.06
    嶈
    -0.06
     درست
    -0.06
     ghép
    -0.06
    POSITIVE LOGITS
    ."-
    0.06
     viac
    0.06
     '-'
    0.06
     contradicting
    0.06
     Pareto
    0.06
     mene
    0.06
    흘
    0.06
    💎
    0.06
     anonym
    0.06
    ^{'
    0.05
    Activations Density 0.001%

    No Known Activations