© 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. 129362
    Prev
    Next
    INDEX
    Explanations

    United States

    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
     omoguć
    -0.07
     umożliw
    -0.07
     hectare
    -0.06
     befindet
    -0.06
     여행
    -0.06
     путеше
    -0.06
     allows
    -0.06
     तेंदुलकर
    -0.06
     prona
    -0.06
     Tato
    -0.06
    POSITIVE LOGITS
     events
    0.07
    करों
    0.06
     ener
    0.06
     спор
    0.06
     athletic
    0.06
     rookie
    0.06
     Athletic
    0.06
    Events
    0.06
    events
    0.06
     sports
    0.06
    Activations Density 0.005%

    No Known Activations