© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117964
    Prev
    Next
    INDEX
    Explanations

    mice gene status

    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
     juillet
    -0.08
     dwa
    -0.06
    AIDS
    -0.06
     機能
    -0.06
    自有
    -0.06
     access
    -0.06
     apoio
    -0.06
     два
    -0.06
    籶
    -0.06
     septiembre
    -0.06
    POSITIVE LOGITS
     impressive
    0.06
     বিভাগের
    0.06
     বিবে
    0.06
     gb
    0.06
     remarkable
    0.06
     sfâr
    0.06
    出现了
    0.05
     increasing
    0.05
    क्रेट
    0.05
    Through
    0.05
    Activations Density 0.013%

    No Known Activations