© 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. 130544
    Prev
    Next
    INDEX
    Explanations

    rules and regulations

    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
     theme
    -0.06
     setelah
    -0.06
     dopo
    -0.06
     disappoint
    -0.06
     نن
    -0.06
     estrategias
    -0.06
    全民
    -0.06
     после
    -0.06
     должны
    -0.06
     strategies
    -0.06
    POSITIVE LOGITS
    简化
    0.07
     smoother
    0.06
     leichter
    0.06
     simplification
    0.06
    Simpl
    0.06
     entrepreneurial
    0.06
     conceivable
    0.06
    减少
    0.06
     bureaucratic
    0.06
     умень
    0.06
    Activations Density 0.020%

    No Known Activations