© 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. 120536
    Prev
    Next
    INDEX
    Explanations

    programming libraries

    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
     errorMessage
    -0.07
     penchant
    -0.07
     συνεχ
    -0.07
     pessimism
    -0.06
     noon
    -0.06
    errorMessage
    -0.06
     वाया
    -0.06
    ciąż
    -0.06
    Ĵ
    -0.06
     vehement
    -0.06
    POSITIVE LOGITS
     erle
    0.07
     facilite
    0.06
    しましょう
    0.06
     svol
    0.06
     travaux
    0.06
     facilitar
    0.06
     Anatom
    0.06
     प्रस्तावित
    0.06
    stream
    0.05
     music
    0.05
    Activations Density 0.002%

    No Known Activations