© 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. 116721
    Prev
    Next
    INDEX
    Explanations

    be, has, produced, prognosis, remarkably, durable

    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
     cramping
    -0.07
     iPod
    -0.06
    iOS
    -0.06
     mobile
    -0.06
     iOS
    -0.06
     QoS
    -0.06
     collective
    -0.06
    جمع
    -0.06
    iPhone
    -0.06
     temporary
    -0.05
    POSITIVE LOGITS
     рік
    0.07
     വര്‍ഷ
    0.07
    めちゃ
    0.07
     veröffentlicht
    0.06
     lentamente
    0.06
     години
    0.06
     در
    0.06
     दिर
    0.06
     في
    0.06
    ត្រ
    0.06
    Activations Density 0.009%

    No Known Activations