© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129819
    Prev
    Next
    INDEX
    Explanations

    code, foreign words, and numbers

    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
    ՝
    -0.06
     surtout
    -0.06
     таких
    -0.06
    そのような
    -0.06
     Formerly
    -0.05
    illa
    -0.05
     experimented
    -0.05
     вся
    -0.05
     booked
    -0.05
     apakah
    -0.05
    POSITIVE LOGITS
     three
    0.07
     플러스
    0.07
     seven
    0.07
    MAJOR
    0.07
     voilà
    0.07
     ardından
    0.07
    તાં
    0.06
     while
    0.06
     após
    0.06
     mientras
    0.06
    Activations Density 0.001%

    No Known Activations