© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118091
    Prev
    Next
    INDEX
    Explanations

    programming keywords and 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
     
    -0.06
    每
    -0.06
    线
    -0.06
    recieve
    -0.06
     konkrét
    -0.06
    小
    -0.06
     etwa
    -0.06
     outperforms
    -0.06
    4
    -0.06
    唦
    -0.05
    POSITIVE LOGITS
     this
    0.10
     .......
    0.09
     .....
    0.09
     ........
    0.09
     ......
    0.09
     ....
    0.08
     この
    0.08
    この
    0.08
     इस
    0.08
     This
    0.08
    Activations Density 0.001%

    No Known Activations