© 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. 120275
    Prev
    Next
    INDEX
    Explanations

    numerical or theoretical study

    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
    की
    -0.06
     கிட்டத்தட்ட
    -0.06
    ducting
    -0.05
    嘚
    -0.05
     why
    -0.05
     timeline
    -0.05
    hz
    -0.05
     Maxwell
    -0.05
     therefore
    -0.05
     daarom
    -0.05
    POSITIVE LOGITS
    attributes
    0.07
     மதிப்பு
    0.06
     borrar
    0.06
    ΡΑ
    0.06
     반드시
    0.06
     помещения
    0.06
     등으로
    0.06
     to
    0.06
     управления
    0.06
     MODELS
    0.06
    Activations Density 0.001%

    No Known Activations