© 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. 117458
    Prev
    Next
    INDEX
    Explanations

    drug dealer, immigration, murder

    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
     connexes
    -0.06
     thể
    -0.06
     mul
    -0.06
    යක්
    -0.06
     प्रत्यक्ष
    -0.05
    收费
    -0.05
    GameState
    -0.05
     ইন্ডি
    -0.05
    ╼
    -0.05
    OPT
    -0.05
    POSITIVE LOGITS
    cold
    0.06
    WAB
    0.06
     entire
    0.06
    uretics
    0.06
     dimmed
    0.06
    akova
    0.06
     Даже
    0.05
     utama
    0.05
     каким
    0.05
     barley
    0.05
    Activations Density 0.001%

    No Known Activations