© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 119504
    Prev
    Next
    INDEX
    Explanations

    parliamentary or governmental discussions

    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
     azt
    -0.06
    首都
    -0.06
     the
    -0.06
    這樣的
    -0.06
     वादा
    -0.06
     integrante
    -0.06
     opportune
    -0.06
     particularmente
    -0.06
    Yet
    -0.06
    assara
    -0.06
    POSITIVE LOGITS
    还是要
    0.05
    வனாக
    0.05
     ही
    0.05
     संबंधी
    0.05
     kuvvet
    0.05
     werden
    0.05
    Portug
    0.05
     hinsichtlich
    0.05
    しかない
    0.05
     रिलेटेड
    0.05
    Activations Density 0.003%

    No Known Activations