© 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. 129009
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    Como
    -0.07
     مثل
    -0.07
     όπως
    -0.07
     ఇటీవల
    -0.07
     बहुतेक
    -0.07
    最初に
    -0.07
     グ
    -0.07
     世界
    -0.07
    Depuis
    -0.07
     日本
    -0.06
    POSITIVE LOGITS
     وكذلك
    0.06
     lac
    0.06
    ↵↵↵↵
    0.06
     Likewise
    0.06
    ),
    0.05
     (
    0.05
     данный
    0.05
    (
    0.05
    만의
    0.05
     encamin
    0.05
    Activations Density 0.003%

    No Known Activations