© 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. 128839
    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
    」，
    -0.07
     تھی۔
    -0.07
    。」
    -0.06
    」。
    -0.06
    :
    -0.06
     keV
    -0.06
     hardly
    -0.05
    ':
    -0.05
    でしたが
    -0.05
     evac
    -0.05
    POSITIVE LOGITS
     andere
    0.08
     andre
    0.07
     বিশেষ
    0.07
     ఇతర
    0.07
    autres
    0.07
     any
    0.07
     другие
    0.07
    特定の
    0.07
     여러
    0.07
     অন্যান্য
    0.07
    Activations Density 0.000%

    No Known Activations