© 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. 116736
    Prev
    Next
    INDEX
    Explanations

    news agencies and press releases

    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
     சமய
    -0.07
    各个
    -0.06
    某个
    -0.06
    某些
    -0.06
     minuscule
    -0.06
     repetitive
    -0.06
    Bitte
    -0.06
    baixo
    -0.06
    练习
    -0.06
     mało
    -0.06
    POSITIVE LOGITS
     завтра
    0.06
    ,
    0.06
     entrepreneurs
    0.06
     people
    0.06
     tomorrow
    0.06
     λειτουργ
    0.06
     está
    0.06
     representations
    0.05
     শঙ্ক
    0.05
     صحبت
    0.05
    Activations Density 0.004%

    No Known Activations