© 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. 117417
    Prev
    Next
    INDEX
    Explanations

    converting to string

    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
     nedeniyle
    -0.06
    㞒
    -0.06
     पर्याप्त
    -0.06
     bevor
    -0.06
    IFEST
    -0.06
    
    -0.06
     eftersom
    -0.06
    并非
    -0.06
     May
    -0.06
    欴
    -0.06
    POSITIVE LOGITS
     ಕೂಡ
    0.06
     untuk
    0.06
     मिळू
    0.06
    La
    0.05
    सुद्धा
    0.05
     militar
    0.05
    尽可能
    0.05
     irmão
    0.05
     già
    0.05
     मूर्ति
    0.05
    Activations Density 0.021%

    No Known Activations