© 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. 129306
    Prev
    Next
    INDEX
    Explanations

    scheduling appointments and events

    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
     penchant
    -0.07
     تنفيذ
    -0.07
     exquisitely
    -0.07
     overly
    -0.06
     stipulated
    -0.06
     gatherings
    -0.06
     konkret
    -0.06
     stated
    -0.06
     itineraries
    -0.06
     energetic
    -0.06
    POSITIVE LOGITS
    可以说
    0.06
     PATCH
    0.06
     جمال
    0.06
    時から
    0.06
    while
    0.06
    शरी
    0.05
     പരിശോധ
    0.05
     revolt
    0.05
     transplant
    0.05
     नहा
    0.05
    Activations Density 0.007%

    No Known Activations