© 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. 117648
    Prev
    Next
    INDEX
    Explanations

    XML structure and code

    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
    的
    -0.06
    Fetch
    -0.05
    amera
    -0.05
     spite
    -0.05
     plasm
    -0.05
     terg
    -0.05
     malgré
    -0.05
     denomin
    -0.05
    upon
    -0.05
     notori
    -0.05
    POSITIVE LOGITS
     for
    0.09
     to
    0.08
     as
    0.08
     vì
    0.07
     เพื่อ
    0.07
     in
    0.07
     để
    0.07
    द्दी
    0.07
     स्मिथ
    0.07
     זה
    0.06
    Activations Density 0.031%

    No Known Activations