© 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. 129549
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
     deemed
    -0.07
     प्रिपरेशन
    -0.06
     medan
    -0.06
    apu
    -0.06
     семь
    -0.06
    ESCAPE
    -0.06
     hoping
    -0.06
     žene
    -0.06
     weitere
    -0.06
     комп
    -0.06
    POSITIVE LOGITS
                               
    0.05
    ليس
    0.05
     নক
    0.05
    index
    0.05
                       
    0.05
     modos
    0.05
    nth
    0.05
    indicator
    0.05
       
    0.05
           
    0.05
    Activations Density 0.006%

    No Known Activations