© 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. 120204
    Prev
    Next
    INDEX
    Explanations

    starting or booting

    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
     inherits
    -0.07
     righteous
    -0.06
    Mar
    -0.06
     improves
    -0.06
     marries
    -0.06
     touted
    -0.06
    එ
    -0.06
     inherit
    -0.06
     heralded
    -0.05
    about
    -0.05
    POSITIVE LOGITS
     adesso
    0.07
    区间
    0.07
     যদি
    0.06
    (´
    0.06
    一面
    0.06
    現状
    0.06
     však
    0.06
    鐧
    0.06
    现有
    0.06
     других
    0.06
    Activations Density 0.011%

    No Known Activations