© 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. 117083
    Prev
    Next
    INDEX
    Explanations

    reading/writing text or data

    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
    accept
    -0.06
     Integr
    -0.06
    长度
    -0.06
     माननीय
    -0.06
     конструкция
    -0.06
    ได้
    -0.05
     സാഹചര്യ
    -0.05
     something
    -0.05
     সমস্যায়
    -0.05
     estilo
    -0.05
    POSITIVE LOGITS
    leValue
    0.06
     گزارش
    0.06
     hablaremos
    0.06
    lemy
    0.06
     niektor
    0.06
    Info
    0.06
     vissa
    0.06
     certaines
    0.06
    
    0.06
     някои
    0.06
    Activations Density 0.003%

    No Known Activations