© 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. 128281
    Prev
    Next
    INDEX
    Explanations

    maximum limit

    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
     Несмотря
    -0.07
     normalcy
    -0.06
     ibid
    -0.06
     mỗi
    -0.06
    Similar
    -0.06
     Zhao
    -0.06
     megfelelő
    -0.06
     rédu
    -0.06
    减少
    -0.06
     moisturizer
    -0.06
    POSITIVE LOGITS
     prevista
    0.06
     inom
    0.06
     sian
    0.06
     القاعد
    0.06
     ihr
    0.06
     güvenlik
    0.05
     intersections
    0.05
    জেলা
    0.05
     ordena
    0.05
     dispersions
    0.05
    Activations Density 0.011%

    No Known Activations