© 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. 118269
    Prev
    Next
    INDEX
    Explanations

    programming language libraries

    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
    我知道
    -0.07
    ೊಳ
    -0.06
    पूर्वी
    -0.06
    我会
    -0.06
     specifico
    -0.05
    展望
    -0.05
     здійс
    -0.05
    僞
    -0.05
    Edited
    -0.05
     छापा
    -0.05
    POSITIVE LOGITS
    ,
    0.07
     Dorset
    0.06
     серви
    0.06
     estas
    0.06
     olarak
    0.06
     превра
    0.06
     antique
    0.06
     could
    0.06
     essas
    0.06
     dari
    0.06
    Activations Density 0.001%

    No Known Activations