© 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. 119848
    Prev
    Next
    INDEX
    Explanations

    armed conflict

    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
     practices
    -0.06
     व्यापारी
    -0.06
     messages
    -0.06
     koost
    -0.05
     আন্তর্জাতিক
    -0.05
    行動
    -0.05
     coworker
    -0.05
     learnings
    -0.05
     शिक्ष
    -0.05
    ricult
    -0.05
    POSITIVE LOGITS
     dysfunctional
    0.07
     Trauma
    0.07
     конфлик
    0.07
     konflikt
    0.07
     stabilisation
    0.07
     stabilization
    0.06
    itale
    0.06
     troubled
    0.06
     conflic
    0.06
     trauma
    0.06
    Activations Density 0.005%

    No Known Activations