© 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. 118527
    Prev
    Next
    INDEX
    Explanations

    line extensions

    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
     rövid
    -0.06
     Uncertain
    -0.06
     selben
    -0.05
     तरल
    -0.05
     اہمیت
    -0.05
    歿
    -0.05
     そう
    -0.05
     Nope
    -0.05
     publicit
    -0.05
     videogame
    -0.05
    POSITIVE LOGITS
     mencari
    0.06
     برای
    0.06
    较为
    0.06
     가능한
    0.06
     `/
    0.06
    เข้าใจ
    0.06
    depend
    0.06
     با
    0.06
    деть
    0.06
    更多的
    0.06
    Activations Density 0.001%

    No Known Activations