© 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. 118146
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

    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
     ஒத்து
    -0.06
     まとめ
    -0.06
     tym
    -0.06
     tři
    -0.06
     Repe
    -0.06
     भीड़
    -0.06
     সবসময়
    -0.05
    ಫ್
    -0.05
     quarrels
    -0.05
     adopted
    -0.05
    POSITIVE LOGITS
     thách
    0.07
     undisclosed
    0.07
     almeno
    0.07
     abelian
    0.06
     some
    0.06
     accurately
    0.06
     algunas
    0.06
     bazı
    0.06
     alcune
    0.06
    ullahi
    0.06
    Activations Density 0.048%

    No Known Activations