© 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. 117993
    Prev
    Next
    INDEX
    Explanations

    variables and initialization

    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
     itu
    -0.07
    =[];
    -0.06
     নানান
    -0.06
       
    -0.06
    ಮಾರ
    -0.06
     etcétera
    -0.06
    取出
    -0.06
    mathrm
    -0.06
    只是
    -0.05
     አይ
    -0.05
    POSITIVE LOGITS
     whose
    0.07
    どちら
    0.07
    Nowadays
    0.07
     which
    0.07
     lutte
    0.07
     WHICH
    0.07
     zowel
    0.06
     Whose
    0.06
    という
    0.06
     både
    0.06
    Activations Density 0.007%

    No Known Activations