© 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. 118279
    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
     российских
    -0.07
     would
    -0.07
    -0.07
    Ბ
    -0.07
     produces
    -0.07
     are
    -0.06
    பெரும்
    -0.06
     other
    -0.06
     were
    -0.06
     may
    -0.06
    POSITIVE LOGITS
    ),
    0.06
    icon
    0.06
     chcete
    0.06
     সংক
    0.06
    when
    0.06
    da
    0.06
    如果您
    0.06
    要知道
    0.05
    as
    0.05
    <eos>
    0.05
    Activations Density 0.000%

    No Known Activations