© 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. 129615
    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
     jednocześnie
    -0.08
    ีย์
    -0.08
    搭配
    -0.07
    同時
    -0.07
     součas
    -0.07
     одновременно
    -0.07
     combina
    -0.07
     Range
    -0.06
     combines
    -0.06
    Además
    -0.06
    POSITIVE LOGITS
     எந்த
    0.06
    7
    0.05
    ;)
    0.05
    5
    0.05
    ரீ
    0.05
    1
    0.05
    2
    0.05
     whether
    0.05
    syllabus
    0.05
     physiologically
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.