© 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. 119149
    Prev
    Next
    INDEX
    Explanations

    error messages or technical issues

    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
     když
    -0.06
     रूई
    -0.06
     powerfully
    -0.06
    नांतर
    -0.06
     комна
    -0.05
     কবল
    -0.05
    ราะห์
    -0.05
     रुचि
    -0.05
     vivos
    -0.05
     Bef
    -0.05
    POSITIVE LOGITS
     may
    0.08
     但
    0.07
     is
    0.07
     這
    0.07
     被
    0.07
     这
    0.07
     principalement
    0.06
    我們
    0.06
     യ
    0.06
     has
    0.06
    Activations Density 0.017%

    No Known Activations