© 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. 120051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     is
    -0.08
     villas
    -0.07
    وی
    -0.07
    에
    -0.06
     PLC
    -0.06
     में
    -0.06
     fenómeno
    -0.06
     rất
    -0.06
     विलय
    -0.06
    、「
    -0.06
    POSITIVE LOGITS
     donc
    0.07
    ∶
    0.06
    จึง
    0.06
     guía
    0.06
    תו
    0.06
     więc
    0.06
     മൂ
    0.06
     учителя
    0.06
     però
    0.06
    することにより
    0.05
    Activations Density 0.002%

    No Known Activations