© 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. 118740
    Prev
    Next
    INDEX
    Explanations

    field identifiers and labels

    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
     attempted
    -0.06
     sucess
    -0.06
    த்தினை
    -0.06
     which
    -0.06
     commenced
    -0.06
     मोबाईल
    -0.06
     Andere
    -0.06
    ostrat
    -0.06
    昨
    -0.06
     tämän
    -0.06
    POSITIVE LOGITS
     contenir
    0.06
    :
    0.06
    的是
    0.06
    স্টি
    0.06
     rétréci
    0.06
     중에서
    0.06
    varez
    0.05
     среди
    0.05
     ไทย
    0.05
     करण्या
    0.05
    Activations Density 0.007%

    No Known Activations