© 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. 129027
    Prev
    Next
    INDEX
    Explanations

    stock ticker symbols

    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
     experienced
    -0.07
    Estos
    -0.07
     diagram
    -0.06
    定義
    -0.06
     neurolog
    -0.06
     drastic
    -0.06
     drastically
    -0.06
    Estas
    -0.06
     திட்டம்
    -0.06
    irti
    -0.06
    POSITIVE LOGITS
    NON
    0.06
     unsolved
    0.06
    nullable
    0.06
     प्रॉब्लम
    0.06
     গি
    0.06
     hidden
    0.05
     only
    0.05
     taxpayers
    0.05
    ことは
    0.05
     unresolved
    0.05
    Activations Density 0.002%

    No Known Activations