© 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. 117602
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces and structures

    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
     मोटरसाइकिल
    -0.06
     транспо
    -0.06
    mini
    -0.06
     :,
    -0.06
    excellence
    -0.06
     திருவ
    -0.06
    Financial
    -0.06
     полноцен
    -0.06
     langsung
    -0.06
     display
    -0.06
    POSITIVE LOGITS
     मुद्दा
    0.06
    关于
    0.06
    ㈱
    0.06
     relação
    0.06
     roasting
    0.06
     फोट
    0.06
    ية
    0.06
     fabb
    0.06
     types
    0.06
    を着
    0.06
    Activations Density 0.008%

    No Known Activations