© 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. 117798
    Prev
    Next
    INDEX
    Explanations

    hosting events and speakers

    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
     لديها
    -0.07
     정책
    -0.06
     maritime
    -0.06
     dachshund
    -0.06
     প্রত্যক্ষ
    -0.06
    Ⴎ
    -0.06
    方案
    -0.06
                 
    -0.06
     stabilit
    -0.06
     चौंका
    -0.06
    POSITIVE LOGITS
     вступи
    0.07
     host
    0.06
    iliate
    0.06
    hosts
    0.06
    上に
    0.05
     opening
    0.05
    主持
    0.05
    <0xE9>
    0.05
     hosting
    0.05
     अर्ज
    0.05
    Activations Density 0.016%

    No Known Activations