© 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. 119946
    Prev
    Next
    INDEX
    Explanations

    error messages and stack traces

    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
    㖦
    -0.06
    🫠
    -0.06
     regulatory
    -0.06
     영향
    -0.06
    チューブ
    -0.06
     bajo
    -0.06
     няма
    -0.06
     Unterkunft
    -0.06
     ไม่มี
    -0.06
     없음
    -0.06
    POSITIVE LOGITS
    2
    0.06
    hingga
    0.06
    と一緒に
    0.06
    itably
    0.06
     हस्ता
    0.06
    지막
    0.06
     která
    0.06
     która
    0.06
    orice
    0.05
     التي
    0.05
    Activations Density 0.001%

    No Known Activations