© 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. 120211
    Prev
    Next
    INDEX
    Explanations

    bend, living, Pawan, SL, receptor, Director

    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
     মসজিদ
    -0.06
    పై
    -0.06
     spol
    -0.06
    瑀
    -0.06
     much
    -0.06
     intermolecular
    -0.06
     যাইহোক
    -0.06
    等待
    -0.06
    NEA
    -0.06
     Accenture
    -0.06
    POSITIVE LOGITS
    并未
    0.06
     足
    0.06
     其
    0.06
     电
    0.06
     ora
    0.06
    일상
    0.06
     ситуа
    0.06
     totaal
    0.06
    ってみ
    0.06
     Raising
    0.05
    Activations Density 0.075%

    No Known Activations