© 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. 118239
    Prev
    Next
    INDEX
    Explanations

    all, always, or

    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
    只有
    -0.08
     only
    -0.08
     continue
    -0.07
    继续
    -0.07
    繼續
    -0.07
     cannot
    -0.07
     have
    -0.06
     продолжа
    -0.06
     عامل
    -0.06
     sadece
    -0.06
    POSITIVE LOGITS
     또는
    0.07
     లేదా
    0.07
     vagy
    0.07
     nebo
    0.07
    Supported
    0.06
     supported
    0.06
     või
    0.06
     or
    0.06
     അല്ലെങ്കിൽ
    0.06
     ឬ
    0.06
    Activations Density 0.027%

    No Known Activations