© 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. 118500
    Prev
    Next
    INDEX
    Explanations

    is a quality professional

    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
     ousted
    -0.08
    什么的
    -0.08
     tweaks
    -0.07
     крупней
    -0.07
    之类的
    -0.06
    сера
    -0.06
     collaborates
    -0.06
     dettaglio
    -0.06
     अणुओं
    -0.06
     spinoff
    -0.06
    POSITIVE LOGITS
     our
    0.08
    আমাদের
    0.08
     нашей
    0.07
     несколь
    0.07
    在我们
    0.07
     multiple
    0.07
     наша
    0.07
     preceding
    0.07
     আমাদের
    0.07
    是我们
    0.07
    Activations Density 0.011%

    No Known Activations