© 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. 119930
    Prev
    Next
    INDEX
    Explanations

    agreement terms and conditions

    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
     अन्य
    -0.07
     চিন্তা
    -0.06
     What
    -0.06
    是什么
    -0.06
    その
    -0.06
     এর
    -0.06
     อะไร
    -0.06
     ماه
    -0.06
    incia
    -0.06
     नए
    -0.06
    POSITIVE LOGITS
     باید
    0.07
     ("[
    0.06
    Cách
    0.06
    unico
    0.06
     criar
    0.06
     правила
    0.06
     చేయ
    0.06
    จริง
    0.06
     треба
    0.06
     verrez
    0.06
    Activations Density 0.001%

    No Known Activations