© 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. 117629
    Prev
    Next
    INDEX
    Explanations

    new places

    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
     spes
    -0.07
    减轻
    -0.06
    விலான
    -0.06
    定价
    -0.06
     pager
    -0.06
     मामले
    -0.06
    Seattle
    -0.06
    减少
    -0.06
    pricing
    -0.06
    amed
    -0.06
    POSITIVE LOGITS
     any
    0.08
     любые
    0.07
    Any
    0.07
     Photos
    0.07
     Bilbao
    0.06
     любую
    0.06
     любой
    0.06
     qualquer
    0.06
     ANY
    0.06
     excited
    0.06
    Activations Density 0.038%

    No Known Activations