© 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. 118281
    Prev
    Next
    INDEX
    Explanations

    reproducibility inter intrac between precision

    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
    齐全
    -0.08
     unexpected
    -0.06
     prompt
    -0.06
     accurate
    -0.06
     additional
    -0.06
     necessary
    -0.06
    sor
    -0.06
    েন্সি
    -0.06
    additional
    -0.06
    unexpected
    -0.06
    POSITIVE LOGITS
     రెండు
    0.06
     subconscious
    0.06
    投資
    0.06
     такі
    0.06
     प्लास्टिक
    0.06
     üçüncü
    0.06
     على
    0.06
     संभावनाएं
    0.06
     ninety
    0.06
     два
    0.06
    Activations Density 0.011%

    No Known Activations