© 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. 118834
    Prev
    Next
    INDEX
    Explanations

    preferences and options

    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
     ভূমিকা
    -0.07
    〗
    -0.06
    時から
    -0.06
    Any
    -0.06
     vaak
    -0.06
    aguars
    -0.06
    ুদ্ধে
    -0.06
    平均
    -0.06
    大于
    -0.06
    പ്പോൾ
    -0.06
    POSITIVE LOGITS
    졔
    0.06
     presto
    0.06
     reusing
    0.06
     perjalanan
    0.06
     Русский
    0.06
    WaitFor
    0.06
    AUTHENT
    0.06
     الطلبه
    0.06
     quickly
    0.05
     senza
    0.05
    Activations Density 0.009%

    No Known Activations