© 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. 130536
    Prev
    Next
    INDEX
    Explanations

    Secret Service, Generally described, Rainbow Song

    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
    精确
    -0.06
     también
    -0.06
     ankaŭ
    -0.06
     supreme
    -0.06
     that
    -0.06
    integral
    -0.05
     exact
    -0.05
     Wordpress
    -0.05
    unc
    -0.05
     pertanto
    -0.05
    POSITIVE LOGITS
     prepara
    0.07
     preparation
    0.07
    pool
    0.07
     patents
    0.07
     persiapan
    0.07
     préparation
    0.06
     container
    0.06
     preparing
    0.06
     определения
    0.06
    Preparation
    0.06
    Activations Density 0.001%

    No Known Activations