© 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. 117636
    Prev
    Next
    INDEX
    Explanations

    constructor parameters

    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
     весьма
    -0.07
     oldukça
    -0.07
     могут
    -0.06
     increíble
    -0.06
     remarkable
    -0.06
     allerede
    -0.06
     ويمكن
    -0.06
    Чтобы
    -0.06
     প্রতিশ্রুতি
    -0.06
    ¸
    -0.06
    POSITIVE LOGITS
     would
    0.06
     needed
    0.06
     needful
    0.06
    TIME
    0.06
     tunique
    0.06
     wyniki
    0.06
    帮忙
    0.06
    needed
    0.05
     সম্পন্ন
    0.05
     extant
    0.05
    Activations Density 0.021%

    No Known Activations