© 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. 117266
    Prev
    Next
    INDEX
    Explanations

    example followed by comma

    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
     Không
    -0.06
     ART
    -0.06
     suis
    -0.06
    मिनी
    -0.06
    চো
    -0.05
     really
    -0.05
     इसे
    -0.05
    FilesIn
    -0.05
     terminé
    -0.05
    umuza
    -0.05
    POSITIVE LOGITS
     may
    0.08
                   
    0.07
     [
    0.07
     might
    0.06
     بعض
    0.06
    也许
    0.06
     lorsque
    0.06
     जब
    0.06
    maybe
    0.06
     ketika
    0.06
    Activations Density 0.013%

    No Known Activations