© 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. 129227
    Prev
    Next
    INDEX
    Explanations

    fictional character

    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
     nome
    -0.06
     வெளிப்புற
    -0.06
     ૩
    -0.06
     பகுதிகளில்
    -0.06
     современных
    -0.06
     кого
    -0.06
     hắn
    -0.06
    스트
    -0.06
     ප්ර
    -0.06
    柔軟
    -0.06
    POSITIVE LOGITS
     we
    0.06
    ผู้
    0.06
     We
    0.06
    itum
    0.06
    yun
    0.06
    Now
    0.06
    Feb
    0.06
     tangible
    0.06
    We
    0.06
    Wang
    0.05
    Activations Density 0.009%

    No Known Activations