© 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. 118065
    Prev
    Next
    INDEX
    Explanations

    places and organizations

    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
    を中心
    -0.07
    を中心に
    -0.07
     বান্ধবী
    -0.07
     whose
    -0.07
     cuja
    -0.06
     defined
    -0.06
    France
    -0.06
    为例
    -0.06
     پتہ
    -0.06
     ফ্রান্স
    -0.06
    POSITIVE LOGITS
     several
    0.07
     কয়েক
    0.06
    several
    0.06
     несколько
    0.06
     niekoľ
    0.06
     đều
    0.06
     varias
    0.05
    1
    0.05
     fairytale
    0.05
    ２
    0.05
    Activations Density 0.067%

    No Known Activations