© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130998
    Prev
    Next
    INDEX
    Explanations

    italics and indicators

    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
    bane
    -0.06
    辜
    -0.06
     ứng
    -0.06
     सक्सेना
    -0.06
    한다
    -0.06
     putting
    -0.06
     Both
    -0.06
     обоих
    -0.06
    ುತ್ತವೆ
    -0.05
     Let
    -0.05
    POSITIVE LOGITS
     он
    0.07
    គាត់
    0.06
    PCS
    0.06
    Renk
    0.06
     mineralization
    0.06
     preacher
    0.06
     on
    0.06
     rejuvenated
    0.06
    )").
    0.06
     DevOps
    0.06
    Activations Density 0.001%

    No Known Activations