© 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. 129709
    Prev
    Next
    INDEX
    Explanations

    HTML code tags

    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
    ↵
    -0.06
     Moda
    -0.06
     uproar
    -0.06
     각종
    -0.06
    4
    -0.05
     Henrik
    -0.05
    ப்பே
    -0.05
     পরিমান
    -0.05
     考え
    -0.05
    㚼
    -0.05
    POSITIVE LOGITS
     یک
    0.08
     a
    0.08
     একটি
    0.08
     एक
    0.07
     an
    0.07
    对
    0.06
     és
    0.06
     während
    0.06
     beautiful
    0.06
     pierws
    0.06
    Activations Density 0.002%

    No Known Activations