© 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. 117346
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

    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
     FERN
    -0.07
    št
    -0.07
     foram
    -0.07
     المعروف
    -0.07
     groundbreaking
    -0.06
    想要的
    -0.06
     распространен
    -0.06
    しましょう
    -0.06
    дума
    -0.06
    
    -0.06
    POSITIVE LOGITS
     by
    0.07
     By
    0.07
    hile
    0.06
    3
    0.06
     wiederum
    0.06
     தமது
    0.06
    By
    0.06
     Red
    0.06
     svoju
    0.06
     In
    0.06
    Activations Density 0.003%

    No Known Activations