© 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. 129356
    Prev
    Next
    INDEX
    Explanations

    names and legal/input contexts

    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
     这个
    -0.07
     数字
    -0.06
     этот
    -0.06
     DIFFICULTY
    -0.06
     সমস্যার
    -0.06
     масштаб
    -0.06
     مشکل
    -0.06
     difficulty
    -0.06
     可以
    -0.06
     मैथमेट
    -0.06
    POSITIVE LOGITS
    anya
    0.07
    Any
    0.07
     any
    0.07
    Pro
    0.07
    their
    0.06
    Ex
    0.06
     get
    0.06
    Out
    0.06
     BiH
    0.06
    ходите
    0.06
    Activations Density 0.001%

    No Known Activations