© 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. 120295
    Prev
    Next
    INDEX
    Explanations

    documentation and code structure

    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
     Corresponding
    -0.06
     corresponding
    -0.06
     Sorry
    -0.06
    Sorry
    -0.06
     sensibilidad
    -0.06
     EdgeInsets
    -0.06
    Corresponding
    -0.06
     fucking
    -0.06
     первое
    -0.05
     wundersch
    -0.05
    POSITIVE LOGITS
     अड्डे
    0.07
     zapewnia
    0.06
     provides
    0.06
     necessitate
    0.06
    provides
    0.06
    ग्राम
    0.06
     improves
    0.06
     barg
    0.06
    Während
    0.06
     Chinatown
    0.06
    Activations Density 0.001%

    No Known Activations