© 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. 128888
    Prev
    Next
    INDEX
    Explanations

    fighter jets, India Sri Lanka, France Iraq

    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
     നിരവധി
    -0.07
     Nationen
    -0.06
     bangsa
    -0.06
    差距
    -0.06
    成為
    -0.06
     अनेक
    -0.06
    ຫວ
    -0.06
     விருப்ப
    -0.06
     நமது
    -0.06
     numerosos
    -0.05
    POSITIVE LOGITS
     Puglia
    0.06
    ્રા
    0.06
     కుమార్
    0.06
    ₎
    0.06
     ORIG
    0.06
    Tablet
    0.06
    ක්ෂ
    0.06
     conveying
    0.06
     knack
    0.06
     পরিবহ
    0.05
    Activations Density 0.057%

    No Known Activations