© 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. 118579
    Prev
    Next
    INDEX
    Explanations

    ```json{ "explanation": "because"}```

    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
     would
    -0.08
     esforços
    -0.07
     for
    -0.07
     থেকে
    -0.07
     நண்ப
    -0.07
     ओनली
    -0.06
     to
    -0.06
     sarebbe
    -0.06
     limpieza
    -0.06
     réduite
    -0.06
    POSITIVE LOGITS
    because
    0.07
    因为
    0.07
     vanwege
    0.07
    因為
    0.07
     because
    0.07
     weil
    0.07
    เพราะ
    0.06
     well
    0.06
     omdat
    0.06
     debido
    0.06
    Activations Density 0.004%

    No Known Activations