© 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. 116392
    Prev
    Next
    INDEX
    Explanations

    commercials

    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
     first
    -0.07
     ஆயிரம்
    -0.07
     nécessite
    -0.07
    都需要
    -0.06
    Terms
    -0.06
    量が
    -0.06
     zuerst
    -0.06
    迄
    -0.06
    MacOS
    -0.06
     veľ
    -0.06
    POSITIVE LOGITS
    HO
    0.06
     verilen
    0.06
     ഔ
    0.06
     excision
    0.05
    药
    0.05
     सेटिंग
    0.05
    ユー
    0.05
    Inserted
    0.05
     contiguous
    0.05
     REG
    0.05
    Activations Density 0.004%

    No Known Activations