© 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. 117043
    Prev
    Next
    INDEX
    Explanations

    Mon, Dim, Micro, team

    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
    thousands
    -0.07
     milhares
    -0.07
     thousands
    -0.07
    自动
    -0.07
     automaty
    -0.07
    自動
    -0.07
     yıll
    -0.07
     miglia
    -0.07
     medzi
    -0.06
     millones
    -0.06
    POSITIVE LOGITS
     team
    0.07
     Mannschaft
    0.07
    チーム
    0.07
    team
    0.07
    团队
    0.06
     فريق
    0.06
     ટીમ
    0.06
     театр
    0.06
    équipe
    0.06
     कानपुर
    0.06
    Activations Density 0.008%

    No Known Activations