© 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. 118449
    Prev
    Next
    INDEX
    Explanations

    reverse order

    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
     additional
    -0.07
     gallon
    -0.07
     individual
    -0.06
     name
    -0.06
     этой
    -0.06
     جديد
    -0.06
    仨
    -0.06
    之后
    -0.06
    additional
    -0.06
    士兵
    -0.06
    POSITIVE LOGITS
    反
    0.08
    reversed
    0.07
     kurang
    0.07
    逆に
    0.07
     reversal
    0.07
     reversed
    0.07
     renversement
    0.06
    逆
    0.06
    來越
    0.06
    自分の
    0.06
    Activations Density 0.002%

    No Known Activations