© 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. 129660
    Prev
    Next
    INDEX
    Explanations

    company abbreviations

    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
    자들이
    -0.06
     restful
    -0.06
    宽度
    -0.06
     sexy
    -0.06
    .**
    -0.06
     naprawdę
    -0.06
     Navier
    -0.06
     Sexy
    -0.06
     )}$
    -0.06
     calmness
    -0.06
    POSITIVE LOGITS
     PROVID
    0.06
     Falle
    0.06
     couvre
    0.06
     barring
    0.06
    ở
    0.06
     Compiled
    0.05
     danse
    0.05
    攢
    0.05
     விளையா
    0.05
     පුද්ග
    0.05
    Activations Density 0.007%

    No Known Activations