© 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. 120680
    Prev
    Next
    INDEX
    Explanations

    expected type or value

    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
     zbog
    -0.07
     достой
    -0.06
     fidèle
    -0.06
     souvent
    -0.06
    spaper
    -0.06
     eigene
    -0.05
    เริ่ม
    -0.05
     spesso
    -0.05
     construire
    -0.05
     überras
    -0.05
    POSITIVE LOGITS
     appears
    0.07
     നാട്ട
    0.06
     данными
    0.06
     gives
    0.06
     place
    0.06
     предпринима
    0.06
    時に
    0.06
     gateway
    0.06
    界面
    0.06
     you
    0.06
    Activations Density 0.002%

    No Known Activations