© 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. 118648
    Prev
    Next
    INDEX
    Explanations

    legislation, statutes, laws

    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
     sebagian
    -0.07
     alcune
    -0.07
     에서
    -0.06
    大部分
    -0.06
    の一部
    -0.06
    forgot
    -0.06
     към
    -0.06
    谆
    -0.06
     minimalism
    -0.06
     तस्वी
    -0.06
    POSITIVE LOGITS
     vždy
    0.07
     always
    0.07
     завжди
    0.06
     zawsze
    0.06
     siempre
    0.06
     uvijek
    0.06
     toujours
    0.06
     sempre
    0.05
     всегда
    0.05
    Always
    0.05
    Activations Density 0.012%

    No Known Activations