© 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. 120226
    Prev
    Next
    INDEX
    Explanations

    police in, active, Q:

    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
    8
    -0.06
    一般来说
    -0.06
    bumper
    -0.06
    omena
    -0.06
     Bird
    -0.06
     first
    -0.06
    isRunning
    -0.06
     Searches
    -0.06
     উদ্দীপ
    -0.06
     ডেভেলপ
    -0.06
    POSITIVE LOGITS
     অন্তত
    0.07
     பகுதியை
    0.06
     の
    0.06
     が
    0.06
     எண்ணிக்கை
    0.06
     минимум
    0.06
    ortheast
    0.06
    處
    0.05
    亞洲
    0.05
     insignificant
    0.05
    Activations Density 0.001%

    No Known Activations