© 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. 130140
    Prev
    Next
    INDEX
    Explanations

    code analysis

    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
     shortage
    -0.07
     increases
    -0.06
     програми
    -0.06
    ினால்
    -0.06
     agreement
    -0.06
     increase
    -0.06
     계획
    -0.06
    agreement
    -0.06
     программи
    -0.06
     विल
    -0.06
    POSITIVE LOGITS
    分析
    0.07
     analy
    0.06
    ర్కొ
    0.06
     seminal
    0.06
     analyzing
    0.06
     charting
    0.06
     corollary
    0.06
     clarifying
    0.06
     защи
    0.06
     cell
    0.06
    Activations Density 0.003%

    No Known Activations