© 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. 120473
    Prev
    Next
    INDEX
    Explanations

    code, software, or names

    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
    提供
    -0.06
     제공
    -0.06
    你需要
    -0.06
    หล่ง
    -0.06
    ijev
    -0.06
     почув
    -0.06
     Provide
    -0.06
     ಹಾಗೂ
    -0.05
     शुरू
    -0.05
     require
    -0.05
    POSITIVE LOGITS
     by
    0.07
    Daw
    0.06
     म्हणजेच
    0.06
    というか
    0.06
    gó
    0.06
     aquellas
    0.05
     फिश
    0.05
     यानि
    0.05
    YO
    0.05
     to
    0.05
    Activations Density 0.001%

    No Known Activations