© 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. 116975
    Prev
    Next
    INDEX
    Explanations

    rapidity range, Q&A, featured in

    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
     দিনের
    -0.07
     decorators
    -0.06
    注射
    -0.06
     Avenger
    -0.06
     जलाश
    -0.06
    如何在
    -0.06
     sneaky
    -0.06
     Verteid
    -0.06
     restructuring
    -0.06
     Kxh
    -0.06
    POSITIVE LOGITS
     nineteen
    0.06
     book
    0.06
     born
    0.06
     fourteen
    0.06
     eighteen
    0.06
     power
    0.06
     ষ্ট
    0.06
     fifteen
    0.06
     बैग
    0.06
     separate
    0.05
    Activations Density 0.002%

    No Known Activations