© 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. 116595
    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
     will
    -0.08
     by
    -0.07
     is
    -0.06
     요즘
    -0.06
     gives
    -0.06
     won
    -0.06
     수행
    -0.06
     may
    -0.06
     eivät
    -0.06
     complex
    -0.06
    POSITIVE LOGITS
    itario
    0.07
    期待
    0.06
    ሉም
    0.06
     allein
    0.06
     однозна
    0.06
     забы
    0.06
     Gebrauch
    0.06
    만을
    0.06
     disregard
    0.06
     consideradas
    0.06
    Activations Density 0.000%

    No Known Activations