© 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. 129099
    Prev
    Next
    INDEX
    Explanations

    SECTION, ro, Molecular, ad

    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
    大多数
    -0.07
     chocol
    -0.06
     чаще
    -0.06
     każdym
    -0.06
     نباش
    -0.06
     vrlo
    -0.06
     often
    -0.06
     called
    -0.06
    药品
    -0.06
     name
    -0.06
    POSITIVE LOGITS
    作为
    0.06
     précéd
    0.06
     Specified
    0.06
     fuentes
    0.06
     Prêmio
    0.06
    amente
    0.06
    车辆
    0.06
     efficiency
    0.06
     Fuentes
    0.06
     usability
    0.06
    Activations Density 0.001%

    No Known Activations