© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129701
    Prev
    Next
    INDEX
    Explanations

    group order and length

    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
     qualunque
    -0.07
    日常
    -0.06
     décisions
    -0.06
    越来越
    -0.06
    のア
    -0.06
    哪个
    -0.06
    охра
    -0.06
    GPIO
    -0.06
     situations
    -0.06
     bhakti
    -0.06
    POSITIVE LOGITS
     jugador
    0.06
     outstanding
    0.06
     پاور
    0.06
     interrelated
    0.06
    ंति
    0.06
    atisf
    0.06
    封面
    0.06
     удалось
    0.06
     szolgált
    0.06
     econom
    0.06
    Activations Density 0.025%

    No Known Activations