© 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. 119645
    Prev
    Next
    INDEX
    Explanations

    XML tags or code identifiers

    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
         
    -0.07
     طراحی
    -0.06
     refinements
    -0.06
    ــ
    -0.06
          
    -0.06
     admirer
    -0.06
    ทั้ง
    -0.06
     expenditures
    -0.06
     जब
    -0.05
    推动
    -0.05
    POSITIVE LOGITS
     کئی
    0.07
     nebo
    0.07
    或
    0.07
     vagy
    0.07
    或其他
    0.06
     beberapa
    0.06
    UK
    0.06
     néhány
    0.06
     некоторых
    0.06
     veya
    0.06
    Activations Density 0.003%

    No Known Activations