© 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. 119822
    Prev
    Next
    INDEX
    Explanations

    default values or fallbacks

    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
     seemingly
    -0.07
     erled
    -0.06
     свободно
    -0.06
     недвижи
    -0.06
    েদ
    -0.06
    ẹo
    -0.06
     prerequisites
    -0.06
    θεση
    -0.06
     depths
    -0.06
    requires
    -0.06
    POSITIVE LOGITS
     fallback
    0.08
    fallback
    0.07
    效果
    0.06
    ۳
    0.06
     muito
    0.06
     최
    0.06
     defaultValue
    0.06
    牲
    0.06
     १०
    0.06
    crawler
    0.06
    Activations Density 0.033%

    No Known Activations