© 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. 129244
    Prev
    Next
    INDEX
    Explanations

    comedian says

    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
    uthers
    -0.06
     का
    -0.06
     मूलभूत
    -0.06
     základ
    -0.06
    ట్ట
    -0.06
     lakini
    -0.06
    ,​
    -0.06
     demanding
    -0.06
     recommended
    -0.06
     зі
    -0.06
    POSITIVE LOGITS
    ↵
    0.07
     bach
    0.06
     aktuell
    0.06
    They
    0.06
     Caed
    0.06
    ỳnh
    0.06
    diagnosis
    0.05
     They
    0.05
    挖掘
    0.05
     Fannie
    0.05
    Activations Density 0.003%

    No Known Activations