© 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. 116872
    Prev
    Next
    INDEX
    Explanations

    theater | opera | politician | historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     calendrier
    -0.07
     margin
    -0.06
     these
    -0.06
    こういう
    -0.06
     Franck
    -0.06
     những
    -0.06
    성이
    -0.06
    성은
    -0.06
     বড়
    -0.06
     rescuing
    -0.06
    POSITIVE LOGITS
     sempre
    0.07
     través
    0.06
     relentlessly
    0.06
     completamente
    0.06
     через
    0.06
     pollutants
    0.06
     invece
    0.06
    通过
    0.05
     miljø
    0.05
    INK
    0.05
    Activations Density 0.013%

    No Known Activations