© 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. 129055
    Prev
    Next
    INDEX
    Explanations

    Q: questions

    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
     Каждый
    -0.07
     פ
    -0.07
     endanger
    -0.06
    Ł
    -0.06
     получать
    -0.06
    諜
    -0.06
     каждый
    -0.05
    ंगर
    -0.05
     aprecia
    -0.05
    Ỡ
    -0.05
    POSITIVE LOGITS
     somit
    0.07
     дъ
    0.06
     Durga
    0.06
    iencia
    0.06
     NW
    0.06
     bạn
    0.06
     argumentos
    0.06
     utilisateurs
    0.06
     ich
    0.06
     vous
    0.06
    Activations Density 0.002%

    No Known Activations