© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118202
    Prev
    Next
    INDEX
    Explanations

    team winning or finishing

    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
     overseeing
    -0.06
    メン
    -0.06
     impatience
    -0.06
    、
    -0.06
    Mem
    -0.06
    使用
    -0.06
     ترکیب
    -0.06
    ukung
    -0.06
    未来
    -0.06
    实现
    -0.06
    POSITIVE LOGITS
     allgeme
    0.07
     allgemein
    0.07
     generally
    0.07
     tems
    0.07
     gost
    0.06
     als
    0.06
    
    0.06
     далеко
    0.06
     Paulista
    0.06
     ಏಕೆಂದರೆ
    0.06
    Activations Density 0.016%

    No Known Activations