© 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. 118880
    Prev
    Next
    INDEX
    Explanations

    transparency and open meetings 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
     सेक्टर
    -0.06
    checkFor
    -0.06
     будут
    -0.06
     will
    -0.06
     their
    -0.06
    夶
    -0.06
    次に
    -0.06
    年から
    -0.06
    들의
    -0.06
     unicorns
    -0.06
    POSITIVE LOGITS
     Meetings
    0.08
    meetings
    0.06
     meetings
    0.06
     transparency
    0.06
     outdoor
    0.06
    Meetings
    0.06
     спорт
    0.06
     secrecy
    0.06
     Transparency
    0.06
     disclosure
    0.06
    Activations Density 0.002%

    No Known Activations