© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117431
    Prev
    Next
    INDEX
    Explanations

    forums and wiki links

    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
     all
    -0.08
    對於
    -0.07
     untuk
    -0.06
     are
    -0.06
    為
    -0.06
     برای
    -0.06
     amikor
    -0.06
     ஆதர
    -0.06
     всех
    -0.06
     উৎপত্তি
    -0.06
    POSITIVE LOGITS
     adhesive
    0.06
     departamentos
    0.06
     departments
    0.06
     harmony
    0.06
     целях
    0.06
    adhesive
    0.06
    illo
    0.06
    пра
    0.06
    ный
    0.05
     departamento
    0.05
    Activations Density 0.004%

    No Known Activations