© 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. 128645
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     into
    -0.06
     for
    -0.06
     over
    -0.06
     sposób
    -0.06
     in
    -0.06
     ALL
    -0.06
     with
    -0.05
    を
    -0.05
     upon
    -0.05
     более
    -0.05
    POSITIVE LOGITS
    這裡
    0.07
    
    0.07
     অনেকগুলি
    0.06
     gyerek
    0.06
    ㅋㅋ
    0.06
    哈哈哈
    0.06
     اینجا
    0.06
     여기서
    0.06
     Ain
    0.06
    病情
    0.06
    Activations Density 0.001%

    No Known Activations