© 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. 129453
    Prev
    Next
    INDEX
    Explanations

    risk of injury in specific demographics

    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
    জু
    -0.06
     Transparent
    -0.06
     রাজধানীতে
    -0.06
    Transparent
    -0.06
     вони
    -0.06
     chante
    -0.06
     шуда
    -0.06
     வட்ட
    -0.06
     после
    -0.06
     luminous
    -0.06
    POSITIVE LOGITS
    桟
    0.06
    レーション
    0.06
     worst
    0.06
     risking
    0.06
    worst
    0.06
     cittadini
    0.06
    ຸ
    0.06
    大家的
    0.06
    Considering
    0.06
    ResourceId
    0.06
    Activations Density 0.095%

    No Known Activations